PRÁCTICA 1_EDA¶

Gozde Yazganoglu/ Irma Sanchez

"This data set used in the CoIL 2000 Challenge contains information on customers of an insurance company. The data consists of 86 variables and includes product usage data and socio-demographic data derived from zip area codes. The data was collected to answer the following question: Can you predict who would be interested in buying a caravan insurance policy and give an explanation why?"¶

En primer lugar importamos las librerías necesarias para realizar el análsis exploratorio de los datos

In [1]:
import pandas as pd
import numpy as np
import sweetviz as sv
import matplotlib.pyplot as plt
from matplotlib import pyplot as plt
import seaborn as sns
import IPython
import warnings
warnings.filterwarnings("ignore")

Definimos nuestros dataframes, extrayendo los datos de los ficheros .txt

In [7]:
data_train = pd.read_table("..//data/raw/ticdata2000.txt", sep="\t", header=None )
data_test = pd.read_table("..//data/raw/ticeval2000.txt", sep="\t", header=None )
df_l0  = pd.read_table("..//data/raw/dfL0.txt",sep=";")
df_l1  = pd.read_table("..//data/raw/dfL1.txt",sep=";")
df_l2  = pd.read_table("..//data/raw/dfL2.txt",sep=";")
df_l3  = pd.read_table("..//data/raw/dfL3.txt",sep=";")
df_l4  = pd.read_table("..//data/raw/dfL4.txt",sep=";")

A través del diccionario de datos, cambiamos los nombres de las columnas, ya que de esta manera obtenemos un data ser mucho más limpio y claro.

In [5]:
data_dict = pd.read_excel("..//data/raw/dictionary.xlsx")
In [8]:
data_dict
Out[8]:
Nr changed name Old Name Description Data Type Unique Values Corresponding values for Categorical values Unnamed: 7
0 1 '1_cust_sub_type', MOSTYPE Customer Subtype Numeric(int64) Array([33, 37, 9, 40, 23, 39, 11, 10, 41, 38,... 1 High Income\n2 Very Important Provincials \n... 21 Young urban have-nots \n22 Mixed apartment ...
1 2 '2_num_houses', MAANTHUI Number of houses Numeric(int64) Array([ 1, 2, 3, 10, 5, 7, 4, 8, 6]) 1-10 NaN
2 3 '3_avg_hh_size', MGEMOMV Avg size household Numeric(int64) Array([3, 2, 4, 1, 5]) 1-6 NaN
3 4 '4_avg_age', MGEMLEEF Avg age Numeric(int64) Array([2, 3, 1, 4, 5, 6]) 1 20-30 years\n2 30-40 years\n3 40-50 years\n4... NaN
4 5 '5_cust_type', MOSHOOFD Customer main type Numeric(int64) Array([ 8, 3, 10, 5, 9, 7, 2, 1, 6, 4]) 1 Successful hedonists\n2 Driven Growers\n3 Av... NaN
... ... ... ... ... ... ... ... ...
81 82 '82_num_ins_boat', APLEZIER Number of boat policies Numeric(int64) Array([0, 2, 1]) NaN NaN
82 83 '83_num_ins_bike', AFIETS Number of bicycle insurance policies Numeric(int64) Array([0, 1, 2, 3]) NaN NaN
83 84 '84_num_ins_property', AINBOED Number of property insurance policies Numeric(int64) Array([0, 1, 2]) NaN NaN
84 85 '85_num_ins_socsec', ABYSTAND Number of social security insurance policies Numeric(int64) Array([0, 1, 2]) NaN NaN
85 86 '86_num_ins_caravan' CARAVAN Number of mobile home policies Numeric(int64) array([0, 1])] 0-1 NaN

86 rows × 8 columns

In [15]:
data_train.columns= ['1_cust_subtype','2_num_houses','3_avg_hh_size','4_avg_age','5_cust_type',
        '6_rel_cat','7_rel_prot','8_rel_other','9_rel_none','10_mar_maried',
        '11_mar_liv_tog','12_mar_other','13_mar_single','14_hh_woclild','15_hh_child',
        '16_educ_high','17_educ_med','18_educ_low','19_ocup_high','20_ocup_entp',
        '21_ocup_farmer','22_ocup_mid_man','23_ocup_skilled','24_ocup_unskilled','25_sc_a',
        '26_sc_b1','27_sc_b2','28_sc_c','29_sc_d','30_home_rent',
        '31_home_ovner','32_car_1','33_car_2','34_car_0','35_health_pub', 
        '36_health_priv','37_income_30','38_income_45','39_income_75','40_income_122',
        '41_income_more','42_income_avg','43_purc_class','44_ins_amnt_3rd','45_ins_firms',
        '46_ins_agr','47_ins_car','48_ins_van','49_ins_moto','50_ins_lorry',
        '51_ins_trailer','52_ins_tractors','53_ins_agr_mach','54_ins_moped','55_ins_life',
        '56_ins_acc_pri','57_ins_acc_fam','58_ins_disab','59_ins_fire','60_ins_surf',
        '61_ins_boat','62_ins_bike','63_ins_property','64_ins_socsec','65_num_ins_3rd',
        '66_num_ins_firms','67_num_ins_agr','68_num_ins_car','69_num_ins_van','70_num_ins_moto',
        '71_num_ins_lorry','72_num_ins_trailer','73_num_ins_tractor','74_num_ins_agrmac','75_num_ins_moped',
        '76_num_ins_life','77_num_ins_acc_pri','78_num_ins_acc_fam','79_num_ins_disab','80_num_ins_fire',
        '81_num_ins_surf','82_num_ins_boat','83_num_ins_bike','84_num_ins_property','85_num_ins_socsec',
        '86_num_ins_caravan']

data_test_columns= ['1_cust_subtype','2_num_houses','3_avg_hh_size','4_avg_age','5_cust_type',
        '6_rel_cat','7_rel_prot','8_rel_other','9_rel_none','10_mar_maried',
        '11_mar_liv_tog','12_mar_other','13_mar_single','14_hh_woclild','15_hh_child',
        '16_educ_high','17_educ_med','18_educ_low','19_ocup_high','20_ocup_entp',
        '21_ocup_farmer','22_ocup_mid_man','23_ocup_skilled','24_ocup_unskilled','25_sc_a',
        '26_sc_b1','27_sc_b2','28_sc_c','29_sc_d','30_home_rent',
        '31_home_ovner','32_car_1','33_car_2','34_car_0','35_health_pub', 
        '36_health_priv','37_income_30','38_income_45','39_income_75','40_income_122',
        '41_income_more','42_income_avg','43_purc_class','44_ins_amnt_3rd','45_ins_firms',
        '46_ins_agr','47_ins_car','48_ins_van','49_ins_moto','50_ins_lorry',
        '51_ins_trailer','52_ins_tractors','53_ins_agr_mach','54_ins_moped','55_ins_life',
        '56_ins_acc_pri','57_ins_acc_fam','58_ins_disab','59_ins_fire','60_ins_surf',
        '61_ins_boat','62_ins_bike','63_ins_property','64_ins_socsec','65_num_ins_3rd',
        '66_num_ins_firms','67_num_ins_agr','68_num_ins_car','69_num_ins_van','70_num_ins_moto',
        '71_num_ins_lorry','72_num_ins_trailer','73_num_ins_tractor','74_num_ins_agrmac','75_num_ins_moped',
        '76_num_ins_life','77_num_ins_acc_pri','78_num_ins_acc_fam','79_num_ins_disab','80_num_ins_fire',
        '81_num_ins_surf','82_num_ins_boat','83_num_ins_bike','84_num_ins_property','85_num_ins_socsec']
In [9]:
data_train
Out[9]:
1_cust_subtype 2_num_houses 3_avg_hh_size 4_avg_age 5_cust_type 6_rel_cat 7_rel_prot 8_rel_other 9_rel_none 10_mar_maried ... 77_num_ins_acc_pri 78_num_ins_acc_fam 79_num_ins_disab 80_num_ins_fire 81_num_ins_surf 82_num_ins_boat 83_num_ins_bike 84_num_ins_property 85_num_ins_socsec 86_num_ins_caravan
0 33 1 3 2 8 0 5 1 3 7 ... 0 0 0 1 0 0 0 0 0 0
1 37 1 2 2 8 1 4 1 4 6 ... 0 0 0 1 0 0 0 0 0 0
2 37 1 2 2 8 0 4 2 4 3 ... 0 0 0 1 0 0 0 0 0 0
3 9 1 3 3 3 2 3 2 4 5 ... 0 0 0 1 0 0 0 0 0 0
4 40 1 4 2 10 1 4 1 4 7 ... 0 0 0 1 0 0 0 0 0 0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
5817 36 1 1 2 8 0 6 1 2 1 ... 0 0 0 1 0 0 0 0 0 0
5818 35 1 4 4 8 1 4 1 4 6 ... 0 0 0 1 0 0 0 0 0 0
5819 33 1 3 4 8 0 6 0 3 5 ... 0 0 0 1 0 0 0 0 0 1
5820 34 1 3 2 8 0 7 0 2 7 ... 0 0 0 0 0 0 0 0 0 0
5821 33 1 3 3 8 0 6 1 2 7 ... 0 0 0 0 0 0 0 0 0 0

5822 rows × 86 columns

A continuación, comprobamos la clase de nuestros datos, y observamos que todos se tratan como tipo 'integer' en ambos data set (training y test)

In [10]:
data_train.dtypes.sort_values().to_frame('feature_type').groupby(by = 'feature_type').size().to_frame('count').reset_index()
Out[10]:
feature_type count
0 int64 86
In [11]:
data_test.dtypes.sort_values().to_frame('feature_type').groupby(by = 'feature_type').size().to_frame('count').reset_index()
Out[11]:
feature_type count
0 int64 85

Ahora, analizaremos si existen valores nulos o duplicados en nuestros datos.

In [12]:
data_train_dtypes = pd.merge(data_train.isnull().sum(axis = 0).sort_values().to_frame('missing_value').reset_index(),
         data_train.dtypes.to_frame('feature_type').reset_index(),
         on = 'index',
         how = 'inner')

data_test_dtypes = pd.merge(data_test.isnull().sum(axis = 0).sort_values().to_frame('missing_value').reset_index(),
         data_test.dtypes.to_frame('feature_type').reset_index(),
         on = 'index',
         how = 'inner')
In [13]:
data_train_dtypes.sort_values(['missing_value', 'feature_type'])
Out[13]:
index missing_value feature_type
0 1_cust_subtype 0 int64
1 62_ins_bike 0 int64
2 61_ins_boat 0 int64
3 60_ins_surf 0 int64
4 59_ins_fire 0 int64
... ... ... ...
81 26_sc_b1 0 int64
82 25_sc_a 0 int64
83 24_ocup_unskilled 0 int64
84 32_car_1 0 int64
85 86_num_ins_caravan 0 int64

86 rows × 3 columns

In [14]:
data_test_dtypes.sort_values(['missing_value', 'feature_type'])
Out[14]:
index missing_value feature_type
0 0 0 int64
1 60 0 int64
2 59 0 int64
3 58 0 int64
4 57 0 int64
... ... ... ...
80 24 0 int64
81 23 0 int64
82 22 0 int64
83 30 0 int64
84 84 0 int64

85 rows × 3 columns

In [15]:
def duplicate_columns(frame):
    groups = frame.columns.to_series().groupby(frame.dtypes).groups
    dups = []

    for t, v in groups.items():

        cs = frame[v].columns
        vs = frame[v]
        lcs = len(cs)

        for i in range(lcs):
            ia = vs.iloc[:,i].values
            for j in range(i+1, lcs):
                ja = vs.iloc[:,j].values
                if np.array_equal(ia, ja):
                    dups.append(cs[i])
                    break
    return dups
In [16]:
duplicate_cols = duplicate_columns(data_train)
In [17]:
duplicate_cols
Out[17]:
[]
In [18]:
duplicate_cols = duplicate_columns(data_test)
In [19]:
duplicate_cols
Out[19]:
[]

Observamos que no existen ni valores nulos ni duplicados en los dos conjuntos de datos (train y test), por tanto no hay que tratar variables nulos.

Análisis de las variables¶

Utilizando sweetviz, obtenemos un primer análisis.

In [24]:
analyze_report=sv.analyze(data_train)
analyze_report.show_html('primer_analisis.html')

                                             |                                                                …
Report primer_analisis.html was generated! NOTEBOOK/COLAB USERS: the web browser MAY not pop up, regardless, the report IS saved in your notebook/colab files.
In [25]:
IPython.display.HTML('primer_analisis.html')# si no funciona display por favor mirar a HTMLs auxiliares.
Out[25]:
DataFrame
NO COMPARISON TARGET
5822
ROWS
602
DUPLICATES
4.0 MB
RAM
86
FEATURES
85
CATEGORICAL
1
NUMERICAL
0
TEXT
2.1.4
Get updates, docs & report issues here
Created & maintained by Francois Bertrand
Graphic design by Jean-Francois Hains
1
1_cust_subtype
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
40
(<1%)
ZEROES:
---
MAX
41.0
95%
39.0
Q3
35.0
MEDIAN
30.0
AVG
24.3
Q1
10.0
5%
3.0
MIN
1.0
RANGE
40.0
IQR
25.0
STD
12.8
VAR
165
KURT.
-1.35
SKEW
-0.435
SUM
141k
2
2_num_houses
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
9
(<1%)
3
3_avg_hh_size
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
5
(<1%)
4
4_avg_age
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
6
(<1%)
5
5_cust_type
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
6
6_rel_cat
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
7
7_rel_prot
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
8
8_rel_other
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
6
(<1%)
9
9_rel_none
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
10
10_mar_maried
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
11
11_mar_liv_tog
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
8
(<1%)
12
12_mar_other
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
13
13_mar_single
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
14
14_hh_woclild
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
15
15_hh_child
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
16
16_educ_high
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
17
17_educ_med
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
18
18_educ_low
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
19
19_ocup_high
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
20
20_ocup_entp
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
6
(<1%)
21
21_ocup_farmer
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
22
22_ocup_mid_man
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
23
23_ocup_skilled
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
24
24_ocup_unskilled
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
25
25_sc_a
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
26
26_sc_b1
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
27
27_sc_b2
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
28
28_sc_c
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
29
29_sc_d
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
9
(<1%)
30
30_home_rent
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
31
31_home_ovner
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
32
32_car_1
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
33
33_car_2
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
8
(<1%)
34
34_car_0
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
35
35_health_pub
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
36
36_health_priv
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
37
37_income_30
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
38
38_income_45
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
39
39_income_75
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
40
40_income_122
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
41
41_income_more
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
8
(<1%)
42
42_income_avg
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
43
43_purc_class
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
8
(<1%)
44
44_ins_amnt_3rd
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
4
(<1%)
45
45_ins_firms
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
7
(<1%)
46
46_ins_agr
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
4
(<1%)
47
47_ins_car
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
6
(<1%)
48
48_ins_van
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
4
(<1%)
49
49_ins_moto
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
6
(<1%)
50
50_ins_lorry
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
4
(<1%)
51
51_ins_trailer
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
6
(<1%)
52
52_ins_tractors
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
5
(<1%)
53
53_ins_agr_mach
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
5
(<1%)
54
54_ins_moped
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
6
(<1%)
55
55_ins_life
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
10
(<1%)
56
56_ins_acc_pri
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
7
(<1%)
57
57_ins_acc_fam
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
58
58_ins_disab
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
5
(<1%)
59
59_ins_fire
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
9
(<1%)
60
60_ins_surf
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
61
61_ins_boat
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
7
(<1%)
62
62_ins_bike
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
2
(<1%)
63
63_ins_property
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
7
(<1%)
64
64_ins_socsec
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
5
(<1%)
65
65_num_ins_3rd
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
66
66_num_ins_firms
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
67
67_num_ins_agr
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
2
(<1%)
68
68_num_ins_car
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
7
(<1%)
69
69_num_ins_van
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
5
(<1%)
70
70_num_ins_moto
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
4
(<1%)
71
71_num_ins_lorry
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
4
(<1%)
72
72_num_ins_trailer
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
4
(<1%)
73
73_num_ins_tractor
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
5
(<1%)
74
74_num_ins_agrmac
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
5
(<1%)
75
75_num_ins_moped
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
76
76_num_ins_life
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
6
(<1%)
77
77_num_ins_acc_pri
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
2
(<1%)
78
78_num_ins_acc_fam
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
2
(<1%)
79
79_num_ins_disab
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
80
80_num_ins_fire
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
7
(<1%)
81
81_num_ins_surf
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
2
(<1%)
82
82_num_ins_boat
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
83
83_num_ins_bike
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
4
(<1%)
84
84_num_ins_property
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
85
85_num_ins_socsec
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
3
(<1%)
86
86_num_ins_caravan
VALUES:
5,822
(100%)
MISSING:
---
DISTINCT:
2
(<1%)
Associations
[Only including dataset "DataFrame"]
■ Squares are categorical associations (uncertainty coefficient & correlation ratio) from 0 to 1. The uncertainty coefficient is assymmetrical, (i.e. ROW LABEL values indicate how much they PROVIDE INFORMATION to each LABEL at the TOP).

• Circles are the symmetrical numerical correlations (Pearson's) from -1 to 1. The trivial diagonal is intentionally left blank for clarity.
Associations
[Only including dataset "None"]
■ Squares are categorical associations (uncertainty coefficient & correlation ratio) from 0 to 1. The uncertainty coefficient is assymmetrical, (i.e. ROW LABEL values indicate how much they PROVIDE INFORMATION to each LABEL at the TOP).

• Circles are the symmetrical numerical correlations (Pearson's) from -1 to 1. The trivial diagonal is intentionally left blank for clarity.
1_cust_subtype
MISSING:
---
>
NUMERICAL ASSOCIATIONS
(PEARSON, -1 to 1)

CATEGORICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
5_cust_type
1.00
43_purc_class
0.77
18_educ_low
0.56
16_educ_high
0.50
19_ocup_high
0.43
28_sc_c
0.42
25_sc_a
0.41
36_health_priv
0.37
35_health_pub
0.37
23_ocup_skilled
0.34
42_income_avg
0.34
17_educ_med
0.30
39_income_75
0.29
24_ocup_unskilled
0.29
MOST FREQUENT VALUES
33
810
13.9%
38
339
5.8%
8
339
5.8%
39
328
5.6%
9
278
4.8%
23
251
4.3%
3
249
4.3%
36
225
3.9%
35
214
3.7%
31
205
3.5%
41
205
3.5%
34
182
3.1%
24
180
3.1%
13
179
3.1%
10
165
2.8%
SMALLEST VALUES
1
124
2.1%
2
82
1.4%
3
249
4.3%
4
52
0.9%
5
45
0.8%
6
119
2.0%
7
44
0.8%
8
339
5.8%
9
278
4.8%
10
165
2.8%
11
153
2.6%
12
111
1.9%
13
179
3.1%
15
5
<0.1%
16
16
0.3%
LARGEST VALUES
41
205
3.5%
40
71
1.2%
39
328
5.6%
38
339
5.8%
37
132
2.3%
36
225
3.9%
35
214
3.7%
34
182
3.1%
33
810
13.9%
32
141
2.4%
31
205
3.5%
30
118
2.0%
29
86
1.5%
28
25
0.4%
27
50
0.9%
2_num_houses
MISSING:
---
TOP CATEGORIES
1
5,267
90%
2
505
9%
3
39
<1%
7
5
<1%
4
2
<1%
10
1
<1%
5
1
<1%
8
1
<1%
6
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
2_num_houses
PROVIDES INFORMATION ON...
61_ins_boat
0.03
56_ins_acc_pri
0.02
23_ocup_skilled
0.02
84_num_ins_property
0.01
4_avg_age
0.01
19_ocup_high
0.01
79_num_ins_disab
0.01
5_cust_type
0.01
58_ins_disab
0.01
25_sc_a
0.01
63_ins_property
0.01
45_ins_firms
0.01
15_hh_child
0.01
50_ins_lorry
0.01

THESE FEATURES
GIVE INFORMATION
ON 2_num_houses:
5_cust_type
0.08
23_ocup_skilled
0.08
19_ocup_high
0.07
15_hh_child
0.07
25_sc_a
0.06
36_health_priv
0.05
35_health_pub
0.05
14_hh_woclild
0.05
4_avg_age
0.05
37_income_30
0.05
39_income_75
0.05
18_educ_low
0.05
12_mar_other
0.04
24_ocup_unskilled
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
2_num_houses
CORRELATION RATIO WITH...
1_cust_subtype
0.06
3_avg_hh_size
MISSING:
---
TOP CATEGORIES
3
2,646
45%
2
2,131
37%
4
693
12%
1
284
5%
5
68
1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
3_avg_hh_size
PROVIDES INFORMATION ON...
15_hh_child
0.26
13_mar_single
0.19
4_avg_age
0.15
10_mar_maried
0.11
12_mar_other
0.11
81_num_ins_surf
0.09
60_ins_surf
0.09
14_hh_woclild
0.07
5_cust_type
0.07
53_ins_agr_mach
0.07
34_car_0
0.06
37_income_30
0.05
74_num_ins_agrmac
0.05
43_purc_class
0.04

THESE FEATURES
GIVE INFORMATION
ON 3_avg_hh_size:
15_hh_child
0.47
13_mar_single
0.29
10_mar_maried
0.19
12_mar_other
0.16
4_avg_age
0.15
5_cust_type
0.13
14_hh_woclild
0.12
34_car_0
0.09
37_income_30
0.09
30_home_rent
0.08
31_home_ovner
0.08
43_purc_class
0.07
39_income_75
0.06
42_income_avg
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
3_avg_hh_size
CORRELATION RATIO WITH...
1_cust_subtype
0.08
4_avg_age
MISSING:
---
TOP CATEGORIES
3
3,000
52%
2
1,452
25%
4
1,073
18%
5
193
3%
1
74
1%
6
30
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
4_avg_age
PROVIDES INFORMATION ON...
3_avg_hh_size
0.15
15_hh_child
0.10
81_num_ins_surf
0.08
5_cust_type
0.07
60_ins_surf
0.07
13_mar_single
0.06
71_num_ins_lorry
0.05
11_mar_liv_tog
0.05
2_num_houses
0.05
14_hh_woclild
0.05
21_ocup_farmer
0.04
12_mar_other
0.04
63_ins_property
0.04
41_income_more
0.04

THESE FEATURES
GIVE INFORMATION
ON 4_avg_age:
15_hh_child
0.18
3_avg_hh_size
0.15
5_cust_type
0.13
13_mar_single
0.09
14_hh_woclild
0.07
12_mar_other
0.07
10_mar_maried
0.07
37_income_30
0.06
43_purc_class
0.05
11_mar_liv_tog
0.05
34_car_0
0.05
17_educ_med
0.05
31_home_ovner
0.04
30_home_rent
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
4_avg_age
CORRELATION RATIO WITH...
1_cust_subtype
0.08
5_cust_type
MISSING:
---
TOP CATEGORIES
8
1,563
27%
3
886
15%
9
667
11%
5
569
10%
1
552
9%
7
550
9%
2
502
9%
10
276
5%
6
205
4%
4
52
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
5_cust_type
PROVIDES INFORMATION ON...
43_purc_class
0.52
60_ins_surf
0.21
53_ins_agr_mach
0.20
74_num_ins_agrmac
0.20
81_num_ins_surf
0.16
21_ocup_farmer
0.14
73_num_ins_tractor
0.14
52_ins_tractors
0.13
71_num_ins_lorry
0.13
4_avg_age
0.13
3_avg_hh_size
0.13
16_educ_high
0.12
50_ins_lorry
0.11
18_educ_low
0.11

THESE FEATURES
GIVE INFORMATION
ON 5_cust_type:
43_purc_class
0.49
18_educ_low
0.12
30_home_rent
0.10
31_home_ovner
0.10
16_educ_high
0.09
10_mar_maried
0.09
28_sc_c
0.08
42_income_avg
0.08
15_hh_child
0.08
25_sc_a
0.08
36_health_priv
0.08
35_health_pub
0.08
4_avg_age
0.07
12_mar_other
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
5_cust_type
CORRELATION RATIO WITH...
1_cust_subtype
1.00
6_rel_cat
MISSING:
---
TOP CATEGORIES
0
3,228
55%
1
1,599
27%
2
733
13%
3
152
3%
4
66
1%
5
18
<1%
6
13
<1%
7
6
<1%
9
4
<1%
8
3
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
6_rel_cat
PROVIDES INFORMATION ON...
60_ins_surf
0.12
41_income_more
0.09
11_mar_liv_tog
0.08
7_rel_prot
0.07
20_ocup_entp
0.06
8_rel_other
0.06
53_ins_agr_mach
0.05
81_num_ins_surf
0.05
40_income_122
0.05
56_ins_acc_pri
0.05
35_health_pub
0.05
36_health_priv
0.04
32_car_1
0.04
34_car_0
0.04

THESE FEATURES
GIVE INFORMATION
ON 6_rel_cat:
7_rel_prot
0.11
11_mar_liv_tog
0.08
35_health_pub
0.08
36_health_priv
0.08
32_car_1
0.07
8_rel_other
0.07
34_car_0
0.06
9_rel_none
0.06
19_ocup_high
0.06
12_mar_other
0.05
18_educ_low
0.05
40_income_122
0.05
16_educ_high
0.05
37_income_30
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
6_rel_cat
CORRELATION RATIO WITH...
1_cust_subtype
0.21
7_rel_prot
MISSING:
---
TOP CATEGORIES
4
1,607
28%
5
1,501
26%
6
714
12%
3
590
10%
7
564
10%
2
396
7%
9
173
3%
1
134
2%
0
78
1%
8
65
1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
7_rel_prot
PROVIDES INFORMATION ON...
9_rel_none
0.32
60_ins_surf
0.20
81_num_ins_surf
0.14
53_ins_agr_mach
0.12
6_rel_cat
0.11
50_ins_lorry
0.11
71_num_ins_lorry
0.11
61_ins_boat
0.10
8_rel_other
0.10
56_ins_acc_pri
0.09
11_mar_liv_tog
0.08
74_num_ins_agrmac
0.08
20_ocup_entp
0.06
33_car_2
0.06

THESE FEATURES
GIVE INFORMATION
ON 7_rel_prot:
9_rel_none
0.30
6_rel_cat
0.07
8_rel_other
0.07
11_mar_liv_tog
0.05
34_car_0
0.05
30_home_rent
0.05
31_home_ovner
0.05
33_car_2
0.05
10_mar_maried
0.05
32_car_1
0.04
12_mar_other
0.04
22_ocup_mid_man
0.04
19_ocup_high
0.04
36_health_priv
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
7_rel_prot
CORRELATION RATIO WITH...
1_cust_subtype
0.12
8_rel_other
MISSING:
---
TOP CATEGORIES
1
2,014
35%
0
2,003
34%
2
1,388
24%
3
257
4%
4
132
2%
5
28
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
8_rel_other
PROVIDES INFORMATION ON...
81_num_ins_surf
0.12
60_ins_surf
0.12
11_mar_liv_tog
0.11
71_num_ins_lorry
0.08
6_rel_cat
0.07
7_rel_prot
0.07
21_ocup_farmer
0.06
53_ins_agr_mach
0.06
34_car_0
0.06
74_num_ins_agrmac
0.06
12_mar_other
0.05
41_income_more
0.05
20_ocup_entp
0.05
79_num_ins_disab
0.05

THESE FEATURES
GIVE INFORMATION
ON 8_rel_other:
11_mar_liv_tog
0.10
7_rel_prot
0.10
34_car_0
0.07
12_mar_other
0.07
10_mar_maried
0.06
6_rel_cat
0.06
9_rel_none
0.06
35_health_pub
0.05
36_health_priv
0.05
30_home_rent
0.05
31_home_ovner
0.05
32_car_1
0.05
21_ocup_farmer
0.05
23_ocup_skilled
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
8_rel_other
CORRELATION RATIO WITH...
1_cust_subtype
0.05
9_rel_none
MISSING:
---
TOP CATEGORIES
3
1,453
25%
4
1,334
23%
2
1,055
18%
5
963
17%
0
456
8%
1
230
4%
6
217
4%
7
101
2%
9
8
<1%
8
5
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
9_rel_none
PROVIDES INFORMATION ON...
7_rel_prot
0.30
60_ins_surf
0.16
50_ins_lorry
0.11
81_num_ins_surf
0.10
71_num_ins_lorry
0.10
56_ins_acc_pri
0.07
11_mar_liv_tog
0.07
74_num_ins_agrmac
0.07
20_ocup_entp
0.06
41_income_more
0.06
61_ins_boat
0.06
6_rel_cat
0.06
58_ins_disab
0.06
8_rel_other
0.06

THESE FEATURES
GIVE INFORMATION
ON 9_rel_none:
7_rel_prot
0.32
10_mar_maried
0.05
30_home_rent
0.05
12_mar_other
0.05
31_home_ovner
0.05
11_mar_liv_tog
0.05
36_health_priv
0.05
35_health_pub
0.05
8_rel_other
0.04
6_rel_cat
0.04
19_ocup_high
0.04
34_car_0
0.04
14_hh_woclild
0.04
22_ocup_mid_man
0.03

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
9_rel_none
CORRELATION RATIO WITH...
1_cust_subtype
0.08
10_mar_maried
MISSING:
---
TOP CATEGORIES
7
1,683
29%
6
1,172
20%
5
946
16%
9
794
14%
8
361
6%
4
324
6%
3
246
4%
2
157
3%
1
75
1%
0
64
1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
10_mar_maried
PROVIDES INFORMATION ON...
12_mar_other
0.55
13_mar_single
0.23
11_mar_liv_tog
0.20
3_avg_hh_size
0.19
34_car_0
0.18
60_ins_surf
0.15
50_ins_lorry
0.11
15_hh_child
0.10
71_num_ins_lorry
0.10
61_ins_boat
0.09
81_num_ins_surf
0.09
5_cust_type
0.09
37_income_30
0.08
32_car_1
0.08

THESE FEATURES
GIVE INFORMATION
ON 10_mar_maried:
12_mar_other
0.52
13_mar_single
0.21
34_car_0
0.16
11_mar_liv_tog
0.13
3_avg_hh_size
0.11
15_hh_child
0.11
5_cust_type
0.09
37_income_30
0.09
31_home_ovner
0.09
30_home_rent
0.09
32_car_1
0.08
36_health_priv
0.07
35_health_pub
0.07
42_income_avg
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
10_mar_maried
CORRELATION RATIO WITH...
1_cust_subtype
0.13
11_mar_liv_tog
MISSING:
---
TOP CATEGORIES
0
2,448
42%
1
2,030
35%
2
1,075
18%
3
159
3%
4
78
1%
5
18
<1%
6
13
<1%
7
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
11_mar_liv_tog
PROVIDES INFORMATION ON...
10_mar_maried
0.13
81_num_ins_surf
0.10
8_rel_other
0.10
60_ins_surf
0.09
71_num_ins_lorry
0.09
50_ins_lorry
0.08
6_rel_cat
0.08
20_ocup_entp
0.07
12_mar_other
0.06
34_car_0
0.05
35_health_pub
0.05
36_health_priv
0.05
4_avg_age
0.05
7_rel_prot
0.05

THESE FEATURES
GIVE INFORMATION
ON 11_mar_liv_tog:
10_mar_maried
0.20
8_rel_other
0.11
12_mar_other
0.09
35_health_pub
0.09
36_health_priv
0.09
7_rel_prot
0.08
34_car_0
0.08
6_rel_cat
0.08
9_rel_none
0.07
30_home_rent
0.06
31_home_ovner
0.06
33_car_2
0.06
5_cust_type
0.05
4_avg_age
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
11_mar_liv_tog
CORRELATION RATIO WITH...
1_cust_subtype
0.05
12_mar_other
MISSING:
---
TOP CATEGORIES
2
1,756
30%
0
1,173
20%
3
1,152
20%
4
648
11%
1
539
9%
5
266
5%
6
179
3%
7
64
1%
9
24
<1%
8
21
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
12_mar_other
PROVIDES INFORMATION ON...
10_mar_maried
0.52
13_mar_single
0.31
34_car_0
0.21
3_avg_hh_size
0.16
60_ins_surf
0.14
50_ins_lorry
0.10
32_car_1
0.09
11_mar_liv_tog
0.09
71_num_ins_lorry
0.09
15_hh_child
0.09
37_income_30
0.09
42_income_avg
0.08
33_car_2
0.08
81_num_ins_surf
0.07

THESE FEATURES
GIVE INFORMATION
ON 12_mar_other:
10_mar_maried
0.55
13_mar_single
0.31
34_car_0
0.21
3_avg_hh_size
0.11
15_hh_child
0.10
37_income_30
0.09
32_car_1
0.09
5_cust_type
0.08
31_home_ovner
0.08
30_home_rent
0.08
42_income_avg
0.07
33_car_2
0.06
35_health_pub
0.06
36_health_priv
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
12_mar_other
CORRELATION RATIO WITH...
1_cust_subtype
0.13
13_mar_single
MISSING:
---
TOP CATEGORIES
0
1,757
30%
2
1,247
21%
1
951
16%
3
848
15%
4
519
9%
5
259
4%
6
127
2%
7
67
1%
8
24
<1%
9
23
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
13_mar_single
PROVIDES INFORMATION ON...
12_mar_other
0.31
3_avg_hh_size
0.29
10_mar_maried
0.21
15_hh_child
0.16
34_car_0
0.12
60_ins_surf
0.11
50_ins_lorry
0.10
37_income_30
0.10
71_num_ins_lorry
0.09
4_avg_age
0.09
29_sc_d
0.08
42_income_avg
0.08
56_ins_acc_pri
0.07
5_cust_type
0.07

THESE FEATURES
GIVE INFORMATION
ON 13_mar_single:
12_mar_other
0.31
10_mar_maried
0.23
3_avg_hh_size
0.19
15_hh_child
0.19
34_car_0
0.12
37_income_30
0.11
30_home_rent
0.09
31_home_ovner
0.09
5_cust_type
0.08
14_hh_woclild
0.07
42_income_avg
0.07
39_income_75
0.06
29_sc_d
0.06
32_car_1
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
13_mar_single
CORRELATION RATIO WITH...
1_cust_subtype
0.10
14_hh_woclild
MISSING:
---
TOP CATEGORIES
3
1,498
26%
4
1,455
25%
2
1,060
18%
5
606
10%
1
372
6%
0
371
6%
6
321
6%
7
96
2%
9
29
<1%
8
14
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
14_hh_woclild
PROVIDES INFORMATION ON...
15_hh_child
0.26
60_ins_surf
0.13
3_avg_hh_size
0.12
71_num_ins_lorry
0.10
61_ins_boat
0.08
4_avg_age
0.07
53_ins_agr_mach
0.07
58_ins_disab
0.07
13_mar_single
0.07
50_ins_lorry
0.07
81_num_ins_surf
0.07
56_ins_acc_pri
0.06
25_sc_a
0.06
27_sc_b2
0.06

THESE FEATURES
GIVE INFORMATION
ON 14_hh_woclild:
15_hh_child
0.29
3_avg_hh_size
0.07
13_mar_single
0.07
17_educ_med
0.05
27_sc_b2
0.05
31_home_ovner
0.05
25_sc_a
0.05
30_home_rent
0.05
4_avg_age
0.05
22_ocup_mid_man
0.05
18_educ_low
0.05
28_sc_c
0.04
37_income_30
0.04
38_income_45
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
14_hh_woclild
CORRELATION RATIO WITH...
1_cust_subtype
0.12
15_hh_child
MISSING:
---
TOP CATEGORIES
4
1,137
20%
5
1,106
19%
3
973
17%
6
783
13%
2
635
11%
7
351
6%
1
292
5%
8
206
4%
9
186
3%
0
153
3%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
15_hh_child
PROVIDES INFORMATION ON...
3_avg_hh_size
0.47
14_hh_woclild
0.29
60_ins_surf
0.19
13_mar_single
0.19
4_avg_age
0.18
81_num_ins_surf
0.13
50_ins_lorry
0.12
10_mar_maried
0.11
12_mar_other
0.10
58_ins_disab
0.10
71_num_ins_lorry
0.09
74_num_ins_agrmac
0.09
61_ins_boat
0.08
5_cust_type
0.08

THESE FEATURES
GIVE INFORMATION
ON 15_hh_child:
3_avg_hh_size
0.26
14_hh_woclild
0.26
13_mar_single
0.16
4_avg_age
0.10
10_mar_maried
0.10
12_mar_other
0.09
5_cust_type
0.08
31_home_ovner
0.07
30_home_rent
0.07
37_income_30
0.06
34_car_0
0.05
39_income_75
0.05
43_purc_class
0.04
22_ocup_mid_man
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
15_hh_child
CORRELATION RATIO WITH...
1_cust_subtype
0.08
16_educ_high
MISSING:
---
TOP CATEGORIES
0
2,147
37%
1
1,322
23%
2
1,144
20%
3
547
9%
4
326
6%
5
187
3%
6
67
1%
7
51
<1%
8
22
<1%
9
9
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
16_educ_high
PROVIDES INFORMATION ON...
25_sc_a
0.26
19_ocup_high
0.17
60_ins_surf
0.17
81_num_ins_surf
0.16
18_educ_low
0.16
41_income_more
0.15
20_ocup_entp
0.12
28_sc_c
0.12
35_health_pub
0.11
36_health_priv
0.11
42_income_avg
0.11
40_income_122
0.11
5_cust_type
0.09
74_num_ins_agrmac
0.09

THESE FEATURES
GIVE INFORMATION
ON 16_educ_high:
25_sc_a
0.27
18_educ_low
0.21
19_ocup_high
0.19
28_sc_c
0.15
35_health_pub
0.13
36_health_priv
0.13
5_cust_type
0.12
42_income_avg
0.11
23_ocup_skilled
0.10
39_income_75
0.09
43_purc_class
0.09
30_home_rent
0.08
31_home_ovner
0.08
40_income_122
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
16_educ_high
CORRELATION RATIO WITH...
1_cust_subtype
0.50
17_educ_med
MISSING:
---
TOP CATEGORIES
4
1,426
24%
3
1,330
23%
2
937
16%
5
738
13%
0
423
7%
1
383
7%
6
348
6%
7
157
3%
9
43
<1%
8
37
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
17_educ_med
PROVIDES INFORMATION ON...
18_educ_low
0.38
26_sc_b1
0.13
71_num_ins_lorry
0.13
60_ins_surf
0.12
29_sc_d
0.11
27_sc_b2
0.10
22_ocup_mid_man
0.10
56_ins_acc_pri
0.09
58_ins_disab
0.09
61_ins_boat
0.08
28_sc_c
0.08
50_ins_lorry
0.08
57_ins_acc_fam
0.08
16_educ_high
0.08

THESE FEATURES
GIVE INFORMATION
ON 17_educ_med:
18_educ_low
0.43
26_sc_b1
0.11
22_ocup_mid_man
0.09
28_sc_c
0.09
27_sc_b2
0.09
29_sc_d
0.08
23_ocup_skilled
0.07
16_educ_high
0.07
25_sc_a
0.06
5_cust_type
0.06
30_home_rent
0.06
19_ocup_high
0.05
31_home_ovner
0.05
14_hh_woclild
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
17_educ_med
CORRELATION RATIO WITH...
1_cust_subtype
0.30
18_educ_low
MISSING:
---
TOP CATEGORIES
5
1,009
17%
6
856
15%
4
851
15%
3
680
12%
2
667
11%
7
640
11%
9
323
6%
0
299
5%
8
254
4%
1
243
4%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
18_educ_low
PROVIDES INFORMATION ON...
17_educ_med
0.43
28_sc_c
0.22
16_educ_high
0.21
25_sc_a
0.20
60_ins_surf
0.17
26_sc_b1
0.16
19_ocup_high
0.14
29_sc_d
0.14
71_num_ins_lorry
0.14
23_ocup_skilled
0.13
5_cust_type
0.12
50_ins_lorry
0.12
42_income_avg
0.11
36_health_priv
0.11

THESE FEATURES
GIVE INFORMATION
ON 18_educ_low:
17_educ_med
0.38
28_sc_c
0.20
16_educ_high
0.16
25_sc_a
0.15
19_ocup_high
0.12
26_sc_b1
0.11
23_ocup_skilled
0.11
5_cust_type
0.11
36_health_priv
0.10
35_health_pub
0.10
29_sc_d
0.09
42_income_avg
0.08
24_ocup_unskilled
0.08
27_sc_b2
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
18_educ_low
CORRELATION RATIO WITH...
1_cust_subtype
0.56
19_ocup_high
MISSING:
---
TOP CATEGORIES
0
1,524
26%
2
1,364
23%
1
1,245
21%
3
756
13%
4
397
7%
5
249
4%
6
138
2%
7
92
2%
9
31
<1%
8
26
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
19_ocup_high
PROVIDES INFORMATION ON...
25_sc_a
0.37
60_ins_surf
0.20
16_educ_high
0.19
36_health_priv
0.16
35_health_pub
0.16
81_num_ins_surf
0.14
28_sc_c
0.13
20_ocup_entp
0.13
41_income_more
0.12
18_educ_low
0.12
24_ocup_unskilled
0.11
23_ocup_skilled
0.10
71_num_ins_lorry
0.10
42_income_avg
0.09

THESE FEATURES
GIVE INFORMATION
ON 19_ocup_high:
25_sc_a
0.35
16_educ_high
0.17
36_health_priv
0.17
35_health_pub
0.17
28_sc_c
0.14
18_educ_low
0.14
24_ocup_unskilled
0.11
23_ocup_skilled
0.11
39_income_75
0.09
22_ocup_mid_man
0.09
42_income_avg
0.08
5_cust_type
0.08
30_home_rent
0.08
31_home_ovner
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
19_ocup_high
CORRELATION RATIO WITH...
1_cust_subtype
0.43
20_ocup_entp
MISSING:
---
TOP CATEGORIES
0
4,171
72%
1
1,202
21%
2
348
6%
5
52
<1%
3
37
<1%
4
12
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
20_ocup_entp
PROVIDES INFORMATION ON...
60_ins_surf
0.17
81_num_ins_surf
0.16
41_income_more
0.11
25_sc_a
0.07
21_ocup_farmer
0.07
16_educ_high
0.06
40_income_122
0.06
19_ocup_high
0.06
29_sc_d
0.06
24_ocup_unskilled
0.05
6_rel_cat
0.05
53_ins_agr_mach
0.04
11_mar_liv_tog
0.04
35_health_pub
0.04

THESE FEATURES
GIVE INFORMATION
ON 20_ocup_entp:
25_sc_a
0.14
19_ocup_high
0.13
16_educ_high
0.12
24_ocup_unskilled
0.11
29_sc_d
0.10
35_health_pub
0.10
36_health_priv
0.10
18_educ_low
0.09
40_income_122
0.09
39_income_75
0.08
23_ocup_skilled
0.08
22_ocup_mid_man
0.08
30_home_rent
0.08
31_home_ovner
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
20_ocup_entp
CORRELATION RATIO WITH...
1_cust_subtype
0.13
21_ocup_farmer
MISSING:
---
TOP CATEGORIES
0
4,176
72%
1
854
15%
2
487
8%
3
143
2%
4
77
1%
5
59
1%
6
14
<1%
8
5
<1%
9
4
<1%
7
3
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
21_ocup_farmer
PROVIDES INFORMATION ON...
60_ins_surf
0.18
53_ins_agr_mach
0.17
74_num_ins_agrmac
0.16
81_num_ins_surf
0.12
73_num_ins_tractor
0.12
52_ins_tractors
0.12
50_ins_lorry
0.11
71_num_ins_lorry
0.10
67_num_ins_agr
0.10
46_ins_agr
0.10
56_ins_acc_pri
0.08
20_ocup_entp
0.08
5_cust_type
0.07
51_ins_trailer
0.06

THESE FEATURES
GIVE INFORMATION
ON 21_ocup_farmer:
5_cust_type
0.14
30_home_rent
0.11
31_home_ovner
0.11
27_sc_b2
0.10
22_ocup_mid_man
0.09
18_educ_low
0.08
24_ocup_unskilled
0.08
25_sc_a
0.08
36_health_priv
0.07
35_health_pub
0.07
28_sc_c
0.07
23_ocup_skilled
0.07
32_car_1
0.07
34_car_0
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
21_ocup_farmer
CORRELATION RATIO WITH...
1_cust_subtype
0.26
22_ocup_mid_man
MISSING:
---
TOP CATEGORIES
2
1,491
26%
3
1,394
24%
4
953
16%
0
667
11%
5
431
7%
1
403
7%
6
211
4%
7
178
3%
9
80
1%
8
14
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
22_ocup_mid_man
PROVIDES INFORMATION ON...
26_sc_b1
0.17
60_ins_surf
0.13
71_num_ins_lorry
0.11
23_ocup_skilled
0.11
53_ins_agr_mach
0.10
21_ocup_farmer
0.09
17_educ_med
0.09
24_ocup_unskilled
0.09
19_ocup_high
0.09
58_ins_disab
0.08
20_ocup_entp
0.08
18_educ_low
0.08
74_num_ins_agrmac
0.08
50_ins_lorry
0.07

THESE FEATURES
GIVE INFORMATION
ON 22_ocup_mid_man:
26_sc_b1
0.14
23_ocup_skilled
0.11
17_educ_med
0.10
18_educ_low
0.09
24_ocup_unskilled
0.09
19_ocup_high
0.08
28_sc_c
0.06
27_sc_b2
0.06
25_sc_a
0.06
16_educ_high
0.06
32_car_1
0.05
35_health_pub
0.05
36_health_priv
0.05
5_cust_type
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
22_ocup_mid_man
CORRELATION RATIO WITH...
1_cust_subtype
0.23
23_ocup_skilled
MISSING:
---
TOP CATEGORIES
2
1,382
24%
0
1,167
20%
3
1,167
20%
1
921
16%
4
604
10%
5
310
5%
6
169
3%
7
68
1%
8
24
<1%
9
10
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
23_ocup_skilled
PROVIDES INFORMATION ON...
28_sc_c
0.17
60_ins_surf
0.11
18_educ_low
0.11
74_num_ins_agrmac
0.11
19_ocup_high
0.11
22_ocup_mid_man
0.11
16_educ_high
0.10
81_num_ins_surf
0.10
25_sc_a
0.10
61_ins_boat
0.09
53_ins_agr_mach
0.08
20_ocup_entp
0.08
71_num_ins_lorry
0.08
56_ins_acc_pri
0.08

THESE FEATURES
GIVE INFORMATION
ON 23_ocup_skilled:
28_sc_c
0.18
18_educ_low
0.13
22_ocup_mid_man
0.11
19_ocup_high
0.10
16_educ_high
0.09
25_sc_a
0.09
36_health_priv
0.08
35_health_pub
0.08
17_educ_med
0.08
24_ocup_unskilled
0.07
5_cust_type
0.07
39_income_75
0.07
26_sc_b1
0.06
30_home_rent
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
23_ocup_skilled
CORRELATION RATIO WITH...
1_cust_subtype
0.34
24_ocup_unskilled
MISSING:
---
TOP CATEGORIES
2
1,439
25%
3
1,109
19%
1
980
17%
0
968
17%
4
772
13%
5
331
6%
6
122
2%
7
66
1%
9
26
<1%
8
9
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
24_ocup_unskilled
PROVIDES INFORMATION ON...
29_sc_d
0.14
60_ins_surf
0.13
19_ocup_high
0.11
20_ocup_entp
0.11
25_sc_a
0.10
22_ocup_mid_man
0.09
41_income_more
0.09
53_ins_agr_mach
0.09
61_ins_boat
0.08
28_sc_c
0.08
18_educ_low
0.08
50_ins_lorry
0.08
21_ocup_farmer
0.08
71_num_ins_lorry
0.08

THESE FEATURES
GIVE INFORMATION
ON 24_ocup_unskilled:
19_ocup_high
0.11
29_sc_d
0.11
18_educ_low
0.09
28_sc_c
0.09
25_sc_a
0.09
22_ocup_mid_man
0.09
30_home_rent
0.08
31_home_ovner
0.07
37_income_30
0.07
23_ocup_skilled
0.07
5_cust_type
0.07
35_health_pub
0.07
16_educ_high
0.07
36_health_priv
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
24_ocup_unskilled
CORRELATION RATIO WITH...
1_cust_subtype
0.29
25_sc_a
MISSING:
---
TOP CATEGORIES
0
1,738
30%
1
1,569
27%
2
1,198
21%
3
685
12%
4
261
4%
5
127
2%
6
96
2%
7
79
1%
9
56
<1%
8
13
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
25_sc_a
PROVIDES INFORMATION ON...
19_ocup_high
0.35
16_educ_high
0.27
60_ins_surf
0.23
81_num_ins_surf
0.17
18_educ_low
0.15
71_num_ins_lorry
0.15
36_health_priv
0.15
35_health_pub
0.15
20_ocup_entp
0.14
28_sc_c
0.13
41_income_more
0.13
39_income_75
0.11
50_ins_lorry
0.10
42_income_avg
0.10

THESE FEATURES
GIVE INFORMATION
ON 25_sc_a:
19_ocup_high
0.37
16_educ_high
0.26
18_educ_low
0.20
36_health_priv
0.17
35_health_pub
0.17
28_sc_c
0.16
39_income_75
0.12
24_ocup_unskilled
0.10
42_income_avg
0.10
23_ocup_skilled
0.10
31_home_ovner
0.09
5_cust_type
0.09
30_home_rent
0.09
29_sc_d
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
25_sc_a
CORRELATION RATIO WITH...
1_cust_subtype
0.41
26_sc_b1
MISSING:
---
TOP CATEGORIES
2
1,783
31%
1
1,480
25%
0
1,353
23%
3
775
13%
4
298
5%
5
78
1%
6
25
<1%
9
17
<1%
8
8
<1%
7
5
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
26_sc_b1
PROVIDES INFORMATION ON...
22_ocup_mid_man
0.14
60_ins_surf
0.12
18_educ_low
0.11
17_educ_med
0.11
29_sc_d
0.10
53_ins_agr_mach
0.08
41_income_more
0.08
16_educ_high
0.08
74_num_ins_agrmac
0.07
28_sc_c
0.07
25_sc_a
0.07
58_ins_disab
0.07
19_ocup_high
0.06
20_ocup_entp
0.06

THESE FEATURES
GIVE INFORMATION
ON 26_sc_b1:
22_ocup_mid_man
0.17
18_educ_low
0.16
17_educ_med
0.13
28_sc_c
0.09
29_sc_d
0.09
16_educ_high
0.08
39_income_75
0.08
23_ocup_skilled
0.08
19_ocup_high
0.07
25_sc_a
0.07
27_sc_b2
0.07
13_mar_single
0.06
24_ocup_unskilled
0.05
37_income_30
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
26_sc_b1
CORRELATION RATIO WITH...
1_cust_subtype
0.24
27_sc_b2
MISSING:
---
TOP CATEGORIES
2
1,676
29%
3
1,175
20%
0
990
17%
1
861
15%
4
652
11%
5
357
6%
6
96
2%
8
7
<1%
7
6
<1%
9
2
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
27_sc_b2
PROVIDES INFORMATION ON...
60_ins_surf
0.23
81_num_ins_surf
0.17
28_sc_c
0.12
21_ocup_farmer
0.10
29_sc_d
0.09
58_ins_disab
0.09
71_num_ins_lorry
0.09
17_educ_med
0.09
50_ins_lorry
0.08
74_num_ins_agrmac
0.08
18_educ_low
0.08
79_num_ins_disab
0.08
53_ins_agr_mach
0.07
25_sc_a
0.07

THESE FEATURES
GIVE INFORMATION
ON 27_sc_b2:
28_sc_c
0.14
18_educ_low
0.10
17_educ_med
0.10
29_sc_d
0.07
25_sc_a
0.07
22_ocup_mid_man
0.06
26_sc_b1
0.06
19_ocup_high
0.06
31_home_ovner
0.06
23_ocup_skilled
0.06
14_hh_woclild
0.06
30_home_rent
0.06
16_educ_high
0.06
13_mar_single
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
27_sc_b2
CORRELATION RATIO WITH...
1_cust_subtype
0.09
28_sc_c
MISSING:
---
TOP CATEGORIES
5
1,168
20%
4
1,159
20%
3
1,090
19%
2
870
15%
6
487
8%
0
364
6%
1
272
5%
7
217
4%
9
124
2%
8
71
1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
28_sc_c
PROVIDES INFORMATION ON...
18_educ_low
0.20
23_ocup_skilled
0.18
25_sc_a
0.16
16_educ_high
0.15
60_ins_surf
0.15
19_ocup_high
0.14
81_num_ins_surf
0.14
27_sc_b2
0.14
36_health_priv
0.10
35_health_pub
0.10
71_num_ins_lorry
0.10
61_ins_boat
0.10
24_ocup_unskilled
0.09
17_educ_med
0.09

THESE FEATURES
GIVE INFORMATION
ON 28_sc_c:
18_educ_low
0.22
23_ocup_skilled
0.17
25_sc_a
0.13
19_ocup_high
0.13
16_educ_high
0.12
27_sc_b2
0.12
36_health_priv
0.10
35_health_pub
0.10
17_educ_med
0.08
5_cust_type
0.08
24_ocup_unskilled
0.08
31_home_ovner
0.08
30_home_rent
0.08
26_sc_b1
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
28_sc_c
CORRELATION RATIO WITH...
1_cust_subtype
0.42
29_sc_d
MISSING:
---
TOP CATEGORIES
0
2,607
45%
1
1,563
27%
2
852
15%
3
441
8%
4
223
4%
5
100
2%
6
22
<1%
7
13
<1%
9
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
29_sc_d
PROVIDES INFORMATION ON...
24_ocup_unskilled
0.11
20_ocup_entp
0.10
81_num_ins_surf
0.09
18_educ_low
0.09
60_ins_surf
0.09
26_sc_b1
0.09
41_income_more
0.08
34_car_0
0.08
17_educ_med
0.08
25_sc_a
0.08
27_sc_b2
0.07
50_ins_lorry
0.07
16_educ_high
0.07
21_ocup_farmer
0.07

THESE FEATURES
GIVE INFORMATION
ON 29_sc_d:
18_educ_low
0.14
24_ocup_unskilled
0.14
17_educ_med
0.11
34_car_0
0.10
26_sc_b1
0.10
27_sc_b2
0.09
25_sc_a
0.09
39_income_75
0.09
31_home_ovner
0.09
30_home_rent
0.09
28_sc_c
0.08
36_health_priv
0.08
35_health_pub
0.08
13_mar_single
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
29_sc_d
CORRELATION RATIO WITH...
1_cust_subtype
0.22
30_home_rent
MISSING:
---
TOP CATEGORIES
0
949
16%
9
760
13%
2
717
12%
3
593
10%
8
532
9%
5
519
9%
4
517
9%
1
428
7%
7
425
7%
6
382
7%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
30_home_rent
PROVIDES INFORMATION ON...
31_home_ovner
0.98
60_ins_surf
0.19
71_num_ins_lorry
0.17
50_ins_lorry
0.15
74_num_ins_agrmac
0.13
81_num_ins_surf
0.13
58_ins_disab
0.12
53_ins_agr_mach
0.11
21_ocup_farmer
0.11
37_income_30
0.11
42_income_avg
0.10
5_cust_type
0.10
41_income_more
0.10
79_num_ins_disab
0.10

THESE FEATURES
GIVE INFORMATION
ON 30_home_rent:
31_home_ovner
0.98
37_income_30
0.10
5_cust_type
0.09
42_income_avg
0.07
18_educ_low
0.07
10_mar_maried
0.07
39_income_75
0.07
36_health_priv
0.07
35_health_pub
0.07
28_sc_c
0.07
13_mar_single
0.07
25_sc_a
0.07
43_purc_class
0.07
12_mar_other
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
30_home_rent
CORRELATION RATIO WITH...
1_cust_subtype
0.27
31_home_ovner
MISSING:
---
TOP CATEGORIES
9
949
16%
0
760
13%
7
724
12%
6
604
10%
1
530
9%
5
520
9%
4
499
9%
8
428
7%
2
426
7%
3
382
7%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
31_home_ovner
PROVIDES INFORMATION ON...
30_home_rent
0.98
60_ins_surf
0.19
71_num_ins_lorry
0.17
50_ins_lorry
0.15
74_num_ins_agrmac
0.13
81_num_ins_surf
0.13
58_ins_disab
0.12
53_ins_agr_mach
0.11
21_ocup_farmer
0.11
37_income_30
0.11
42_income_avg
0.10
5_cust_type
0.10
79_num_ins_disab
0.10
41_income_more
0.10

THESE FEATURES
GIVE INFORMATION
ON 31_home_ovner:
30_home_rent
0.98
37_income_30
0.10
5_cust_type
0.09
42_income_avg
0.07
10_mar_maried
0.07
39_income_75
0.07
35_health_pub
0.07
28_sc_c
0.07
18_educ_low
0.07
36_health_priv
0.07
25_sc_a
0.07
13_mar_single
0.07
43_purc_class
0.07
12_mar_other
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
31_home_ovner
CORRELATION RATIO WITH...
1_cust_subtype
0.26
32_car_1
MISSING:
---
TOP CATEGORIES
6
1,663
29%
7
1,413
24%
5
1,210
21%
9
505
9%
4
448
8%
8
261
4%
3
231
4%
2
58
<1%
0
19
<1%
1
14
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
32_car_1
PROVIDES INFORMATION ON...
34_car_0
0.35
33_car_2
0.19
60_ins_surf
0.18
81_num_ins_surf
0.12
53_ins_agr_mach
0.10
74_num_ins_agrmac
0.09
12_mar_other
0.09
71_num_ins_lorry
0.09
10_mar_maried
0.08
50_ins_lorry
0.07
6_rel_cat
0.07
61_ins_boat
0.07
21_ocup_farmer
0.07
58_ins_disab
0.06

THESE FEATURES
GIVE INFORMATION
ON 32_car_1:
34_car_0
0.34
33_car_2
0.15
12_mar_other
0.09
10_mar_maried
0.08
30_home_rent
0.06
31_home_ovner
0.06
37_income_30
0.06
13_mar_single
0.06
36_health_priv
0.05
22_ocup_mid_man
0.05
35_health_pub
0.05
5_cust_type
0.05
39_income_75
0.05
29_sc_d
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
32_car_1
CORRELATION RATIO WITH...
1_cust_subtype
0.20
33_car_2
MISSING:
---
TOP CATEGORIES
0
1,854
32%
2
1,748
30%
1
1,468
25%
3
385
7%
4
301
5%
5
56
<1%
6
9
<1%
7
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
33_car_2
PROVIDES INFORMATION ON...
60_ins_surf
0.20
32_car_1
0.15
81_num_ins_surf
0.14
71_num_ins_lorry
0.09
50_ins_lorry
0.08
61_ins_boat
0.07
20_ocup_entp
0.07
34_car_0
0.07
12_mar_other
0.06
58_ins_disab
0.06
36_health_priv
0.06
35_health_pub
0.06
53_ins_agr_mach
0.06
56_ins_acc_pri
0.06

THESE FEATURES
GIVE INFORMATION
ON 33_car_2:
32_car_1
0.19
30_home_rent
0.08
34_car_0
0.08
31_home_ovner
0.08
36_health_priv
0.08
35_health_pub
0.08
12_mar_other
0.08
10_mar_maried
0.07
7_rel_prot
0.06
5_cust_type
0.05
11_mar_liv_tog
0.05
19_ocup_high
0.04
23_ocup_skilled
0.04
15_hh_child
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
33_car_2
CORRELATION RATIO WITH...
1_cust_subtype
0.08
34_car_0
MISSING:
---
TOP CATEGORIES
2
1,625
28%
0
1,450
25%
3
1,066
18%
1
776
13%
4
587
10%
5
174
3%
6
89
2%
7
25
<1%
9
17
<1%
8
13
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
34_car_0
PROVIDES INFORMATION ON...
32_car_1
0.34
12_mar_other
0.21
10_mar_maried
0.16
81_num_ins_surf
0.16
60_ins_surf
0.15
13_mar_single
0.12
36_health_priv
0.10
29_sc_d
0.10
35_health_pub
0.10
3_avg_hh_size
0.09
42_income_avg
0.09
37_income_30
0.09
50_ins_lorry
0.08
33_car_2
0.08

THESE FEATURES
GIVE INFORMATION
ON 34_car_0:
32_car_1
0.35
12_mar_other
0.21
10_mar_maried
0.18
13_mar_single
0.12
36_health_priv
0.11
35_health_pub
0.11
37_income_30
0.10
42_income_avg
0.09
29_sc_d
0.08
30_home_rent
0.08
31_home_ovner
0.08
5_cust_type
0.08
43_purc_class
0.07
33_car_2
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
34_car_0
CORRELATION RATIO WITH...
1_cust_subtype
0.18
35_health_pub
MISSING:
---
TOP CATEGORIES
7
1,511
26%
5
974
17%
6
875
15%
9
852
15%
8
699
12%
4
357
6%
2
307
5%
3
177
3%
0
55
<1%
1
15
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
35_health_pub
PROVIDES INFORMATION ON...
36_health_priv
0.99
60_ins_surf
0.26
81_num_ins_surf
0.26
19_ocup_high
0.17
25_sc_a
0.17
71_num_ins_lorry
0.15
16_educ_high
0.13
42_income_avg
0.11
34_car_0
0.11
41_income_more
0.11
50_ins_lorry
0.10
28_sc_c
0.10
18_educ_low
0.10
20_ocup_entp
0.10

THESE FEATURES
GIVE INFORMATION
ON 35_health_pub:
36_health_priv
0.99
19_ocup_high
0.16
25_sc_a
0.15
16_educ_high
0.11
18_educ_low
0.11
28_sc_c
0.10
34_car_0
0.10
42_income_avg
0.09
31_home_ovner
0.08
30_home_rent
0.08
5_cust_type
0.08
23_ocup_skilled
0.08
39_income_75
0.07
10_mar_maried
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
35_health_pub
CORRELATION RATIO WITH...
1_cust_subtype
0.37
36_health_priv
MISSING:
---
TOP CATEGORIES
2
1,511
26%
4
992
17%
0
852
15%
3
849
15%
1
699
12%
5
364
6%
7
307
5%
6
178
3%
9
55
<1%
8
15
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
36_health_priv
PROVIDES INFORMATION ON...
35_health_pub
0.99
60_ins_surf
0.26
81_num_ins_surf
0.26
19_ocup_high
0.17
25_sc_a
0.17
71_num_ins_lorry
0.15
16_educ_high
0.13
34_car_0
0.11
42_income_avg
0.11
41_income_more
0.11
50_ins_lorry
0.10
28_sc_c
0.10
18_educ_low
0.10
20_ocup_entp
0.10

THESE FEATURES
GIVE INFORMATION
ON 36_health_priv:
35_health_pub
0.99
19_ocup_high
0.16
25_sc_a
0.15
16_educ_high
0.11
18_educ_low
0.11
28_sc_c
0.10
34_car_0
0.10
42_income_avg
0.09
30_home_rent
0.08
31_home_ovner
0.08
5_cust_type
0.08
23_ocup_skilled
0.08
39_income_75
0.07
10_mar_maried
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
36_health_priv
CORRELATION RATIO WITH...
1_cust_subtype
0.37
37_income_30
MISSING:
---
TOP CATEGORIES
0
1,304
22%
2
1,094
19%
3
1,079
19%
1
630
11%
4
599
10%
5
568
10%
6
293
5%
7
156
3%
9
51
<1%
8
48
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
37_income_30
PROVIDES INFORMATION ON...
42_income_avg
0.27
60_ins_surf
0.19
39_income_75
0.15
81_num_ins_surf
0.13
38_income_45
0.13
13_mar_single
0.11
71_num_ins_lorry
0.10
34_car_0
0.10
40_income_122
0.10
31_home_ovner
0.10
30_home_rent
0.10
12_mar_other
0.09
3_avg_hh_size
0.09
74_num_ins_agrmac
0.09

THESE FEATURES
GIVE INFORMATION
ON 37_income_30:
42_income_avg
0.22
39_income_75
0.15
38_income_45
0.13
31_home_ovner
0.11
30_home_rent
0.11
13_mar_single
0.10
34_car_0
0.09
12_mar_other
0.09
10_mar_maried
0.08
5_cust_type
0.07
18_educ_low
0.07
24_ocup_unskilled
0.07
43_purc_class
0.06
40_income_122
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
37_income_30
CORRELATION RATIO WITH...
1_cust_subtype
0.22
38_income_45
MISSING:
---
TOP CATEGORIES
4
1,356
23%
3
1,147
20%
5
931
16%
2
919
16%
0
465
8%
6
406
7%
1
268
5%
7
205
4%
9
90
2%
8
35
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
38_income_45
PROVIDES INFORMATION ON...
60_ins_surf
0.24
81_num_ins_surf
0.19
37_income_30
0.13
39_income_75
0.12
41_income_more
0.11
42_income_avg
0.11
50_ins_lorry
0.11
71_num_ins_lorry
0.10
53_ins_agr_mach
0.10
61_ins_boat
0.10
58_ins_disab
0.08
40_income_122
0.08
56_ins_acc_pri
0.08
74_num_ins_agrmac
0.07

THESE FEATURES
GIVE INFORMATION
ON 38_income_45:
37_income_30
0.13
39_income_75
0.12
42_income_avg
0.09
25_sc_a
0.06
16_educ_high
0.06
18_educ_low
0.05
28_sc_c
0.05
40_income_122
0.05
35_health_pub
0.05
36_health_priv
0.05
27_sc_b2
0.05
19_ocup_high
0.04
24_ocup_unskilled
0.04
29_sc_d
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
38_income_45
CORRELATION RATIO WITH...
1_cust_subtype
0.22
39_income_75
MISSING:
---
TOP CATEGORIES
3
1,215
21%
2
1,165
20%
4
1,034
18%
0
891
15%
1
657
11%
5
498
9%
6
125
2%
7
93
2%
9
91
2%
8
53
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
39_income_75
PROVIDES INFORMATION ON...
42_income_avg
0.22
60_ins_surf
0.19
37_income_30
0.15
81_num_ins_surf
0.13
71_num_ins_lorry
0.13
25_sc_a
0.12
38_income_45
0.12
50_ins_lorry
0.12
74_num_ins_agrmac
0.10
19_ocup_high
0.09
16_educ_high
0.09
61_ins_boat
0.09
29_sc_d
0.09
53_ins_agr_mach
0.09

THESE FEATURES
GIVE INFORMATION
ON 39_income_75:
42_income_avg
0.18
37_income_30
0.15
38_income_45
0.12
25_sc_a
0.11
19_ocup_high
0.09
30_home_rent
0.08
31_home_ovner
0.08
18_educ_low
0.08
16_educ_high
0.08
35_health_pub
0.07
36_health_priv
0.07
5_cust_type
0.07
29_sc_d
0.07
43_purc_class
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
39_income_75
CORRELATION RATIO WITH...
1_cust_subtype
0.29
40_income_122
MISSING:
---
TOP CATEGORIES
0
3,246
56%
1
1,359
23%
2
736
13%
3
246
4%
4
147
3%
5
71
1%
6
8
<1%
9
4
<1%
8
4
<1%
7
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
40_income_122
PROVIDES INFORMATION ON...
42_income_avg
0.19
60_ins_surf
0.18
41_income_more
0.12
81_num_ins_surf
0.11
20_ocup_entp
0.09
16_educ_high
0.08
74_num_ins_agrmac
0.06
37_income_30
0.06
25_sc_a
0.06
63_ins_property
0.06
35_health_pub
0.06
19_ocup_high
0.06
36_health_priv
0.06
6_rel_cat
0.05

THESE FEATURES
GIVE INFORMATION
ON 40_income_122:
42_income_avg
0.25
16_educ_high
0.11
37_income_30
0.10
35_health_pub
0.09
36_health_priv
0.09
31_home_ovner
0.09
30_home_rent
0.09
19_ocup_high
0.08
38_income_45
0.08
25_sc_a
0.08
18_educ_low
0.07
28_sc_c
0.07
24_ocup_unskilled
0.07
39_income_75
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
40_income_122
CORRELATION RATIO WITH...
1_cust_subtype
0.19
41_income_more
MISSING:
---
TOP CATEGORIES
0
4,900
84%
1
763
13%
2
96
2%
3
36
<1%
4
24
<1%
9
1
<1%
5
1
<1%
7
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
41_income_more
PROVIDES INFORMATION ON...
20_ocup_entp
0.07
42_income_avg
0.07
40_income_122
0.05
16_educ_high
0.05
6_rel_cat
0.04
25_sc_a
0.04
19_ocup_high
0.04
29_sc_d
0.03
38_income_45
0.03
36_health_priv
0.03
35_health_pub
0.03
26_sc_b1
0.03
63_ins_property
0.03
24_ocup_unskilled
0.03

THESE FEATURES
GIVE INFORMATION
ON 41_income_more:
42_income_avg
0.20
16_educ_high
0.15
25_sc_a
0.13
40_income_122
0.12
19_ocup_high
0.12
38_income_45
0.11
36_health_priv
0.11
35_health_pub
0.11
20_ocup_entp
0.11
30_home_rent
0.10
31_home_ovner
0.10
6_rel_cat
0.09
24_ocup_unskilled
0.09
29_sc_d
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
41_income_more
CORRELATION RATIO WITH...
1_cust_subtype
0.15
42_income_avg
MISSING:
---
TOP CATEGORIES
3
1,932
33%
4
1,854
32%
5
733
13%
2
651
11%
6
355
6%
7
131
2%
8
70
1%
1
49
<1%
0
25
<1%
9
22
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
42_income_avg
PROVIDES INFORMATION ON...
40_income_122
0.25
37_income_30
0.22
41_income_more
0.20
39_income_75
0.18
60_ins_surf
0.16
16_educ_high
0.11
25_sc_a
0.10
81_num_ins_surf
0.10
38_income_45
0.09
36_health_priv
0.09
35_health_pub
0.09
34_car_0
0.09
43_purc_class
0.08
19_ocup_high
0.08

THESE FEATURES
GIVE INFORMATION
ON 42_income_avg:
37_income_30
0.27
39_income_75
0.22
40_income_122
0.19
38_income_45
0.11
18_educ_low
0.11
36_health_priv
0.11
35_health_pub
0.11
16_educ_high
0.11
31_home_ovner
0.10
30_home_rent
0.10
5_cust_type
0.10
43_purc_class
0.10
25_sc_a
0.10
19_ocup_high
0.09

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
42_income_avg
CORRELATION RATIO WITH...
1_cust_subtype
0.34
43_purc_class
MISSING:
---
TOP CATEGORIES
3
1,524
26%
4
902
15%
6
901
15%
1
587
10%
5
583
10%
7
474
8%
8
426
7%
2
425
7%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
43_purc_class
PROVIDES INFORMATION ON...
5_cust_type
0.49
60_ins_surf
0.17
74_num_ins_agrmac
0.12
53_ins_agr_mach
0.12
81_num_ins_surf
0.11
71_num_ins_lorry
0.10
42_income_avg
0.10
61_ins_boat
0.09
16_educ_high
0.09
50_ins_lorry
0.08
18_educ_low
0.08
56_ins_acc_pri
0.08
19_ocup_high
0.07
3_avg_hh_size
0.07

THESE FEATURES
GIVE INFORMATION
ON 43_purc_class:
5_cust_type
0.52
18_educ_low
0.09
42_income_avg
0.08
30_home_rent
0.08
31_home_ovner
0.08
16_educ_high
0.07
19_ocup_high
0.07
36_health_priv
0.06
35_health_pub
0.06
39_income_75
0.06
37_income_30
0.06
34_car_0
0.06
25_sc_a
0.06
28_sc_c
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
43_purc_class
CORRELATION RATIO WITH...
1_cust_subtype
0.77
44_ins_amnt_3rd
MISSING:
---
TOP CATEGORIES
0
3,482
60%
2
2,128
37%
1
201
3%
3
11
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
44_ins_amnt_3rd
PROVIDES INFORMATION ON...
65_num_ins_3rd
1.00
80_num_ins_fire
0.23
59_ins_fire
0.14
67_num_ins_agr
0.09
46_ins_agr
0.08
58_ins_disab
0.07
75_num_ins_moped
0.05
76_num_ins_life
0.05
79_num_ins_disab
0.05
55_ins_life
0.05
54_ins_moped
0.05
78_num_ins_acc_fam
0.04
60_ins_surf
0.04
57_ins_acc_fam
0.04

THESE FEATURES
GIVE INFORMATION
ON 44_ins_amnt_3rd:
65_num_ins_3rd
0.84
59_ins_fire
0.26
80_num_ins_fire
0.23
47_ins_car
0.02
68_num_ins_car
0.02
54_ins_moped
0.02
75_num_ins_moped
0.02
55_ins_life
0.02
76_num_ins_life
0.01
5_cust_type
0.01
46_ins_agr
0.01
67_num_ins_agr
0.01
43_purc_class
0.01
15_hh_child
0.01

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
44_ins_amnt_3rd
CORRELATION RATIO WITH...
1_cust_subtype
0.05
45_ins_firms
MISSING:
---
TOP CATEGORIES
0
5,740
99%
2
30
<1%
3
23
<1%
4
17
<1%
1
7
<1%
6
4
<1%
5
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
45_ins_firms
PROVIDES INFORMATION ON...
66_num_ins_firms
0.99
50_ins_lorry
0.27
71_num_ins_lorry
0.24
58_ins_disab
0.20
79_num_ins_disab
0.19
69_num_ins_van
0.17
48_ins_van
0.15
74_num_ins_agrmac
0.14
53_ins_agr_mach
0.14
51_ins_trailer
0.05
72_num_ins_trailer
0.05
73_num_ins_tractor
0.02
52_ins_tractors
0.02
63_ins_property
0.02

THESE FEATURES
GIVE INFORMATION
ON 45_ins_firms:
66_num_ins_firms
0.79
59_ins_fire
0.14
69_num_ins_van
0.10
48_ins_van
0.08
5_cust_type
0.06
30_home_rent
0.06
31_home_ovner
0.06
58_ins_disab
0.06
15_hh_child
0.06
79_num_ins_disab
0.06
27_sc_b2
0.06
18_educ_low
0.05
38_income_45
0.05
28_sc_c
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
45_ins_firms
CORRELATION RATIO WITH...
1_cust_subtype
0.04
46_ins_agr
MISSING:
---
TOP CATEGORIES
0
5,702
98%
4
60
1%
3
57
<1%
2
3
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
46_ins_agr
PROVIDES INFORMATION ON...
67_num_ins_agr
1.00
73_num_ins_tractor
0.30
52_ins_tractors
0.27
74_num_ins_agrmac
0.14
53_ins_agr_mach
0.13
72_num_ins_trailer
0.04
51_ins_trailer
0.04
58_ins_disab
0.04
79_num_ins_disab
0.03
56_ins_acc_pri
0.03
77_num_ins_acc_pri
0.02
59_ins_fire
0.02
80_num_ins_fire
0.01
65_num_ins_3rd
0.01

THESE FEATURES
GIVE INFORMATION
ON 46_ins_agr:
67_num_ins_agr
0.86
73_num_ins_tractor
0.34
52_ins_tractors
0.34
59_ins_fire
0.29
80_num_ins_fire
0.10
5_cust_type
0.10
21_ocup_farmer
0.10
44_ins_amnt_3rd
0.08
65_num_ins_3rd
0.08
43_purc_class
0.05
31_home_ovner
0.04
30_home_rent
0.04
18_educ_low
0.04
68_num_ins_car
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
46_ins_agr
CORRELATION RATIO WITH...
1_cust_subtype
0.08
47_ins_car
MISSING:
---
TOP CATEGORIES
0
2,845
49%
6
2,319
40%
5
613
11%
7
41
<1%
8
3
<1%
4
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
47_ins_car
PROVIDES INFORMATION ON...
68_num_ins_car
0.83
71_num_ins_lorry
0.10
50_ins_lorry
0.09
74_num_ins_agrmac
0.09
53_ins_agr_mach
0.09
60_ins_surf
0.09
75_num_ins_moped
0.08
86_num_ins_caravan
0.07
51_ins_trailer
0.07
54_ins_moped
0.07
64_ins_socsec
0.07
85_num_ins_socsec
0.06
72_num_ins_trailer
0.06
61_ins_boat
0.06

THESE FEATURES
GIVE INFORMATION
ON 47_ins_car:
68_num_ins_car
0.72
59_ins_fire
0.03
54_ins_moped
0.02
75_num_ins_moped
0.02
86_num_ins_caravan
0.02
44_ins_amnt_3rd
0.02
65_num_ins_3rd
0.01
5_cust_type
0.01
30_home_rent
0.01
31_home_ovner
0.01
80_num_ins_fire
0.01
55_ins_life
0.01
64_ins_socsec
0.01
23_ocup_skilled
0.01

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
47_ins_car
CORRELATION RATIO WITH...
1_cust_subtype
0.02
48_ins_van
MISSING:
---
TOP CATEGORIES
0
5,774
>99%
6
35
<1%
5
10
<1%
7
3
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
48_ins_van
PROVIDES INFORMATION ON...
69_num_ins_van
0.94
50_ins_lorry
0.29
71_num_ins_lorry
0.28
74_num_ins_agrmac
0.16
53_ins_agr_mach
0.13
45_ins_firms
0.08
66_num_ins_firms
0.08
72_num_ins_trailer
0.04
51_ins_trailer
0.04
79_num_ins_disab
0.03
58_ins_disab
0.02
73_num_ins_tractor
0.01
52_ins_tractors
0.01
55_ins_life
0.01

THESE FEATURES
GIVE INFORMATION
ON 48_ins_van:
69_num_ins_van
0.92
45_ins_firms
0.15
59_ins_fire
0.11
66_num_ins_firms
0.10
74_num_ins_agrmac
0.08
50_ins_lorry
0.07
53_ins_agr_mach
0.07
71_num_ins_lorry
0.07
51_ins_trailer
0.06
72_num_ins_trailer
0.05
17_educ_med
0.05
47_ins_car
0.05
35_health_pub
0.05
36_health_priv
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
48_ins_van
CORRELATION RATIO WITH...
1_cust_subtype
0.03
49_ins_moto
MISSING:
---
TOP CATEGORIES
0
5,600
96%
4
136
2%
6
49
<1%
5
32
<1%
3
3
<1%
7
2
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
49_ins_moto
PROVIDES INFORMATION ON...
70_num_ins_moto
0.97
56_ins_acc_pri
0.03
51_ins_trailer
0.02
77_num_ins_acc_pri
0.01
72_num_ins_trailer
0.01
48_ins_van
0.01
64_ins_socsec
0.01
79_num_ins_disab
0.01
58_ins_disab
0.01
69_num_ins_van
0.01
61_ins_boat
0.01
63_ins_property
0.01
82_num_ins_boat
0.01
45_ins_firms
0.01

THESE FEATURES
GIVE INFORMATION
ON 49_ins_moto:
70_num_ins_moto
0.82
5_cust_type
0.03
43_purc_class
0.02
38_income_45
0.02
59_ins_fire
0.02
22_ocup_mid_man
0.02
68_num_ins_car
0.02
13_mar_single
0.02
42_income_avg
0.02
12_mar_other
0.02
10_mar_maried
0.02
7_rel_prot
0.02
15_hh_child
0.02
30_home_rent
0.02

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
49_ins_moto
CORRELATION RATIO WITH...
1_cust_subtype
0.04
50_ins_lorry
MISSING:
---
TOP CATEGORIES
0
5,813
>99%
6
7
<1%
4
1
<1%
9
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
50_ins_lorry
PROVIDES INFORMATION ON...
71_num_ins_lorry
0.94
69_num_ins_van
0.07
48_ins_van
0.07
45_ins_firms
0.04
53_ins_agr_mach
0.03
66_num_ins_firms
0.03
74_num_ins_agrmac
0.03
51_ins_trailer
0.02
72_num_ins_trailer
0.02
79_num_ins_disab
0.02
58_ins_disab
0.02
73_num_ins_tractor
0.01
52_ins_tractors
0.01
83_num_ins_bike
0.00

THESE FEATURES
GIVE INFORMATION
ON 50_ins_lorry:
71_num_ins_lorry
0.96
48_ins_van
0.29
69_num_ins_van
0.28
45_ins_firms
0.27
66_num_ins_firms
0.17
30_home_rent
0.15
31_home_ovner
0.15
59_ins_fire
0.13
51_ins_trailer
0.13
15_hh_child
0.12
39_income_75
0.12
18_educ_low
0.12
5_cust_type
0.11
21_ocup_farmer
0.11

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
50_ins_lorry
CORRELATION RATIO WITH...
1_cust_subtype
0.02
51_ins_trailer
MISSING:
---
TOP CATEGORIES
0
5,757
99%
2
38
<1%
1
19
<1%
3
6
<1%
5
1
<1%
4
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
51_ins_trailer
PROVIDES INFORMATION ON...
72_num_ins_trailer
0.99
60_ins_surf
0.13
71_num_ins_lorry
0.13
50_ins_lorry
0.13
81_num_ins_surf
0.12
74_num_ins_agrmac
0.10
53_ins_agr_mach
0.09
69_num_ins_van
0.07
48_ins_van
0.06
79_num_ins_disab
0.04
45_ins_firms
0.04
58_ins_disab
0.04
61_ins_boat
0.03
66_num_ins_firms
0.03

THESE FEATURES
GIVE INFORMATION
ON 51_ins_trailer:
72_num_ins_trailer
0.89
5_cust_type
0.08
47_ins_car
0.07
21_ocup_farmer
0.06
59_ins_fire
0.06
30_home_rent
0.05
31_home_ovner
0.05
69_num_ins_van
0.05
45_ins_firms
0.05
36_health_priv
0.05
28_sc_c
0.05
12_mar_other
0.05
43_purc_class
0.05
24_ocup_unskilled
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
51_ins_trailer
CORRELATION RATIO WITH...
1_cust_subtype
0.04
52_ins_tractors
MISSING:
---
TOP CATEGORIES
0
5,679
98%
3
79
1%
5
28
<1%
4
27
<1%
6
9
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
52_ins_tractors
PROVIDES INFORMATION ON...
73_num_ins_tractor
0.92
67_num_ins_agr
0.39
46_ins_agr
0.34
53_ins_agr_mach
0.26
74_num_ins_agrmac
0.26
50_ins_lorry
0.09
71_num_ins_lorry
0.09
79_num_ins_disab
0.05
58_ins_disab
0.05
56_ins_acc_pri
0.04
51_ins_trailer
0.03
45_ins_firms
0.03
69_num_ins_van
0.03
72_num_ins_trailer
0.03

THESE FEATURES
GIVE INFORMATION
ON 52_ins_tractors:
73_num_ins_tractor
0.86
46_ins_agr
0.27
67_num_ins_agr
0.27
59_ins_fire
0.24
5_cust_type
0.13
21_ocup_farmer
0.12
30_home_rent
0.06
31_home_ovner
0.06
53_ins_agr_mach
0.05
43_purc_class
0.05
80_num_ins_fire
0.05
74_num_ins_agrmac
0.05
68_num_ins_car
0.04
27_sc_b2
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
52_ins_tractors
CORRELATION RATIO WITH...
1_cust_subtype
0.10
53_ins_agr_mach
MISSING:
---
TOP CATEGORIES
0
5,801
>99%
4
8
<1%
3
6
<1%
2
4
<1%
6
3
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
53_ins_agr_mach
PROVIDES INFORMATION ON...
74_num_ins_agrmac
0.91
69_num_ins_van
0.07
71_num_ins_lorry
0.07
48_ins_van
0.07
50_ins_lorry
0.07
52_ins_tractors
0.05
73_num_ins_tractor
0.05
79_num_ins_disab
0.04
58_ins_disab
0.04
45_ins_firms
0.04
72_num_ins_trailer
0.04
56_ins_acc_pri
0.04
51_ins_trailer
0.04
66_num_ins_firms
0.03

THESE FEATURES
GIVE INFORMATION
ON 53_ins_agr_mach:
74_num_ins_agrmac
0.88
52_ins_tractors
0.26
59_ins_fire
0.25
73_num_ins_tractor
0.25
5_cust_type
0.20
21_ocup_farmer
0.17
45_ins_firms
0.14
69_num_ins_van
0.13
48_ins_van
0.13
46_ins_agr
0.13
67_num_ins_agr
0.12
43_purc_class
0.12
7_rel_prot
0.12
30_home_rent
0.11

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
53_ins_agr_mach
CORRELATION RATIO WITH...
1_cust_subtype
0.06
54_ins_moped
MISSING:
---
TOP CATEGORIES
0
5,426
93%
3
282
5%
4
63
1%
2
34
<1%
5
16
<1%
6
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
54_ins_moped
PROVIDES INFORMATION ON...
75_num_ins_moped
0.97
80_num_ins_fire
0.03
68_num_ins_car
0.02
53_ins_agr_mach
0.02
47_ins_car
0.02
65_num_ins_3rd
0.02
44_ins_amnt_3rd
0.02
59_ins_fire
0.02
66_num_ins_firms
0.01
74_num_ins_agrmac
0.01
84_num_ins_property
0.01
77_num_ins_acc_pri
0.01
69_num_ins_van
0.01
82_num_ins_boat
0.01

THESE FEATURES
GIVE INFORMATION
ON 54_ins_moped:
75_num_ins_moped
0.81
59_ins_fire
0.07
80_num_ins_fire
0.07
68_num_ins_car
0.07
47_ins_car
0.07
44_ins_amnt_3rd
0.05
65_num_ins_3rd
0.05
5_cust_type
0.02
15_hh_child
0.02
7_rel_prot
0.02
43_purc_class
0.02
38_income_45
0.02
16_educ_high
0.02
21_ocup_farmer
0.02

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
54_ins_moped
CORRELATION RATIO WITH...
1_cust_subtype
0.05
55_ins_life
MISSING:
---
TOP CATEGORIES
0
5,529
95%
4
94
2%
3
84
1%
6
38
<1%
5
35
<1%
2
28
<1%
1
9
<1%
7
3
<1%
9
1
<1%
8
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
55_ins_life
PROVIDES INFORMATION ON...
76_num_ins_life
0.84
78_num_ins_acc_fam
0.11
57_ins_acc_fam
0.11
74_num_ins_agrmac
0.05
53_ins_agr_mach
0.05
56_ins_acc_pri
0.04
77_num_ins_acc_pri
0.04
48_ins_van
0.04
69_num_ins_van
0.03
45_ins_firms
0.03
63_ins_property
0.02
64_ins_socsec
0.02
61_ins_boat
0.02
66_num_ins_firms
0.02

THESE FEATURES
GIVE INFORMATION
ON 55_ins_life:
76_num_ins_life
0.73
59_ins_fire
0.06
44_ins_amnt_3rd
0.05
65_num_ins_3rd
0.04
5_cust_type
0.04
80_num_ins_fire
0.03
18_educ_low
0.03
17_educ_med
0.03
39_income_75
0.03
38_income_45
0.03
43_purc_class
0.03
31_home_ovner
0.03
25_sc_a
0.03
19_ocup_high
0.03

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
55_ins_life
CORRELATION RATIO WITH...
1_cust_subtype
0.07
56_ins_acc_pri
MISSING:
---
TOP CATEGORIES
0
5,791
>99%
2
18
<1%
3
4
<1%
4
3
<1%
1
3
<1%
6
2
<1%
5
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
56_ins_acc_pri
PROVIDES INFORMATION ON...
77_num_ins_acc_pri
1.00
74_num_ins_agrmac
0.06
53_ins_agr_mach
0.05
61_ins_boat
0.01
52_ins_tractors
0.01
73_num_ins_tractor
0.01
46_ins_agr
0.01
67_num_ins_agr
0.01
82_num_ins_boat
0.01
55_ins_life
0.01
49_ins_moto
0.01
76_num_ins_life
0.00
51_ins_trailer
0.00
21_ocup_farmer
0.00

THESE FEATURES
GIVE INFORMATION
ON 56_ins_acc_pri:
77_num_ins_acc_pri
0.83
30_home_rent
0.10
31_home_ovner
0.10
36_health_priv
0.09
35_health_pub
0.09
7_rel_prot
0.09
18_educ_low
0.09
17_educ_med
0.09
5_cust_type
0.09
59_ins_fire
0.09
21_ocup_farmer
0.08
38_income_45
0.08
23_ocup_skilled
0.08
43_purc_class
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
56_ins_acc_pri
CORRELATION RATIO WITH...
1_cust_subtype
0.03
57_ins_acc_fam
MISSING:
---
TOP CATEGORIES
0
5,784
>99%
2
25
<1%
3
13
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
57_ins_acc_fam
PROVIDES INFORMATION ON...
78_num_ins_acc_fam
1.00
64_ins_socsec
0.03
85_num_ins_socsec
0.03
55_ins_life
0.02
76_num_ins_life
0.02
83_num_ins_bike
0.01
63_ins_property
0.01
73_num_ins_tractor
0.00
52_ins_tractors
0.00
51_ins_trailer
0.00
84_num_ins_property
0.00
86_num_ins_caravan
0.00
67_num_ins_agr
0.00
46_ins_agr
0.00

THESE FEATURES
GIVE INFORMATION
ON 57_ins_acc_fam:
78_num_ins_acc_fam
0.90
55_ins_life
0.11
76_num_ins_life
0.09
17_educ_med
0.08
18_educ_low
0.07
64_ins_socsec
0.07
59_ins_fire
0.06
39_income_75
0.06
5_cust_type
0.06
30_home_rent
0.05
14_hh_woclild
0.05
85_num_ins_socsec
0.05
31_home_ovner
0.05
25_sc_a
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
57_ins_acc_fam
CORRELATION RATIO WITH...
1_cust_subtype
0.02
58_ins_disab
MISSING:
---
TOP CATEGORIES
0
5,799
>99%
6
19
<1%
7
2
<1%
4
1
<1%
5
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
58_ins_disab
PROVIDES INFORMATION ON...
79_num_ins_disab
0.94
66_num_ins_firms
0.07
45_ins_firms
0.06
53_ins_agr_mach
0.04
71_num_ins_lorry
0.04
50_ins_lorry
0.04
74_num_ins_agrmac
0.03
51_ins_trailer
0.01
48_ins_van
0.01
73_num_ins_tractor
0.01
69_num_ins_van
0.01
72_num_ins_trailer
0.01
52_ins_tractors
0.01
46_ins_agr
0.01

THESE FEATURES
GIVE INFORMATION
ON 58_ins_disab:
79_num_ins_disab
0.92
45_ins_firms
0.20
66_num_ins_firms
0.18
59_ins_fire
0.16
31_home_ovner
0.12
30_home_rent
0.12
15_hh_child
0.10
27_sc_b2
0.09
17_educ_med
0.09
38_income_45
0.08
22_ocup_mid_man
0.08
39_income_75
0.08
10_mar_maried
0.07
35_health_pub
0.07

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
58_ins_disab
CORRELATION RATIO WITH...
1_cust_subtype
0.03
59_ins_fire
MISSING:
---
TOP CATEGORIES
0
2,666
46%
4
1,226
21%
3
920
16%
2
535
9%
1
161
3%
6
155
3%
5
149
3%
7
9
<1%
8
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
59_ins_fire
PROVIDES INFORMATION ON...
80_num_ins_fire
0.88
67_num_ins_agr
0.32
65_num_ins_3rd
0.31
74_num_ins_agrmac
0.29
46_ins_agr
0.29
44_ins_amnt_3rd
0.26
73_num_ins_tractor
0.26
53_ins_agr_mach
0.25
52_ins_tractors
0.24
58_ins_disab
0.16
79_num_ins_disab
0.15
45_ins_firms
0.14
50_ins_lorry
0.13
66_num_ins_firms
0.13

THESE FEATURES
GIVE INFORMATION
ON 59_ins_fire:
80_num_ins_fire
0.47
44_ins_amnt_3rd
0.14
65_num_ins_3rd
0.14
5_cust_type
0.06
30_home_rent
0.04
31_home_ovner
0.04
43_purc_class
0.03
52_ins_tractors
0.02
73_num_ins_tractor
0.02
46_ins_agr
0.02
67_num_ins_agr
0.02
10_mar_maried
0.02
21_ocup_farmer
0.02
34_car_0
0.02

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
59_ins_fire
CORRELATION RATIO WITH...
1_cust_subtype
0.09
60_ins_surf
MISSING:
---
TOP CATEGORIES
0
5,819
>99%
1
2
<1%
3
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
60_ins_surf
PROVIDES INFORMATION ON...
81_num_ins_surf
1.00
61_ins_boat
0.02
82_num_ins_boat
0.02
63_ins_property
0.01
84_num_ins_property
0.01
51_ins_trailer
0.01
72_num_ins_trailer
0.01
86_num_ins_caravan
0.00
20_ocup_entp
0.00
21_ocup_farmer
0.00
40_income_122
0.00
33_car_2
0.00
25_sc_a
0.00
35_health_pub
0.00

THESE FEATURES
GIVE INFORMATION
ON 60_ins_surf:
81_num_ins_surf
0.93
35_health_pub
0.26
36_health_priv
0.26
38_income_45
0.24
61_ins_boat
0.23
25_sc_a
0.23
27_sc_b2
0.23
5_cust_type
0.21
33_car_2
0.20
19_ocup_high
0.20
7_rel_prot
0.20
39_income_75
0.19
37_income_30
0.19
15_hh_child
0.19

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
60_ins_surf
CORRELATION RATIO WITH...
1_cust_subtype
0.02
61_ins_boat
MISSING:
---
TOP CATEGORIES
0
5,789
>99%
4
13
<1%
1
5
<1%
2
5
<1%
3
5
<1%
6
3
<1%
5
2
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
61_ins_boat
PROVIDES INFORMATION ON...
82_num_ins_boat
0.97
60_ins_surf
0.23
81_num_ins_surf
0.23
51_ins_trailer
0.02
63_ins_property
0.02
72_num_ins_trailer
0.02
84_num_ins_property
0.02
77_num_ins_acc_pri
0.02
56_ins_acc_pri
0.01
86_num_ins_caravan
0.01
64_ins_socsec
0.00
46_ins_agr
0.00
2_num_houses
0.00
67_num_ins_agr
0.00

THESE FEATURES
GIVE INFORMATION
ON 61_ins_boat:
82_num_ins_boat
0.80
5_cust_type
0.10
18_educ_low
0.10
7_rel_prot
0.10
38_income_45
0.10
28_sc_c
0.10
30_home_rent
0.09
10_mar_maried
0.09
31_home_ovner
0.09
39_income_75
0.09
43_purc_class
0.09
23_ocup_skilled
0.09
17_educ_med
0.08
24_ocup_unskilled
0.08

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
61_ins_boat
CORRELATION RATIO WITH...
1_cust_subtype
0.03
62_ins_bike
MISSING:
---
TOP CATEGORIES
0
5,675
97%
1
147
3%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
62_ins_bike
PROVIDES INFORMATION ON...
83_num_ins_bike
0.88
71_num_ins_lorry
0.03
50_ins_lorry
0.01
57_ins_acc_fam
0.01
66_num_ins_firms
0.00
77_num_ins_acc_pri
0.00
82_num_ins_boat
0.00
45_ins_firms
0.00
79_num_ins_disab
0.00
58_ins_disab
0.00
56_ins_acc_pri
0.00
74_num_ins_agrmac
0.00
61_ins_boat
0.00
53_ins_agr_mach
0.00

THESE FEATURES
GIVE INFORMATION
ON 62_ins_bike:
83_num_ins_bike
1.00
24_ocup_unskilled
0.02
59_ins_fire
0.02
21_ocup_farmer
0.02
32_car_1
0.02
12_mar_other
0.01
18_educ_low
0.01
43_purc_class
0.01
34_car_0
0.01
42_income_avg
0.01
19_ocup_high
0.01
10_mar_maried
0.01
9_rel_none
0.01
16_educ_high
0.01

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
62_ins_bike
CORRELATION RATIO WITH...
1_cust_subtype
0.01
63_ins_property
MISSING:
---
TOP CATEGORIES
0
5,777
>99%
1
18
<1%
2
16
<1%
3
6
<1%
4
3
<1%
6
1
<1%
5
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
63_ins_property
PROVIDES INFORMATION ON...
84_num_ins_property
0.99
60_ins_surf
0.16
81_num_ins_surf
0.15
61_ins_boat
0.03
51_ins_trailer
0.02
82_num_ins_boat
0.01
72_num_ins_trailer
0.01
45_ins_firms
0.01
57_ins_acc_fam
0.01
64_ins_socsec
0.01
78_num_ins_acc_fam
0.01
66_num_ins_firms
0.01
85_num_ins_socsec
0.01
76_num_ins_life
0.00

THESE FEATURES
GIVE INFORMATION
ON 63_ins_property:
84_num_ins_property
0.82
36_health_priv
0.10
35_health_pub
0.09
28_sc_c
0.08
18_educ_low
0.08
10_mar_maried
0.08
5_cust_type
0.07
16_educ_high
0.07
25_sc_a
0.07
39_income_75
0.07
12_mar_other
0.07
15_hh_child
0.07
23_ocup_skilled
0.07
43_purc_class
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
63_ins_property
CORRELATION RATIO WITH...
1_cust_subtype
0.05
64_ins_socsec
MISSING:
---
TOP CATEGORIES
0
5,740
99%
4
44
<1%
3
22
<1%
2
15
<1%
5
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
64_ins_socsec
PROVIDES INFORMATION ON...
85_num_ins_socsec
0.99
78_num_ins_acc_fam
0.07
57_ins_acc_fam
0.07
82_num_ins_boat
0.02
63_ins_property
0.01
61_ins_boat
0.01
84_num_ins_property
0.01
48_ins_van
0.01
68_num_ins_car
0.01
69_num_ins_van
0.01
86_num_ins_caravan
0.01
55_ins_life
0.01
47_ins_car
0.01
52_ins_tractors
0.01

THESE FEATURES
GIVE INFORMATION
ON 64_ins_socsec:
85_num_ins_socsec
0.84
68_num_ins_car
0.07
47_ins_car
0.07
5_cust_type
0.06
30_home_rent
0.05
31_home_ovner
0.05
59_ins_fire
0.05
43_purc_class
0.05
10_mar_maried
0.05
13_mar_single
0.05
17_educ_med
0.05
34_car_0
0.05
37_income_30
0.05
7_rel_prot
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
64_ins_socsec
CORRELATION RATIO WITH...
1_cust_subtype
0.06
65_num_ins_3rd
MISSING:
---
TOP CATEGORIES
0
3,482
60%
1
2,334
40%
2
6
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
65_num_ins_3rd
PROVIDES INFORMATION ON...
44_ins_amnt_3rd
0.84
80_num_ins_fire
0.23
59_ins_fire
0.14
67_num_ins_agr
0.08
46_ins_agr
0.08
75_num_ins_moped
0.05
54_ins_moped
0.05
76_num_ins_life
0.04
55_ins_life
0.04
78_num_ins_acc_fam
0.04
48_ins_van
0.04
57_ins_acc_fam
0.04
60_ins_surf
0.03
69_num_ins_van
0.03

THESE FEATURES
GIVE INFORMATION
ON 65_num_ins_3rd:
44_ins_amnt_3rd
1.00
59_ins_fire
0.31
80_num_ins_fire
0.27
54_ins_moped
0.02
75_num_ins_moped
0.02
47_ins_car
0.02
68_num_ins_car
0.02
55_ins_life
0.02
76_num_ins_life
0.02
46_ins_agr
0.01
67_num_ins_agr
0.01
5_cust_type
0.01
15_hh_child
0.01
43_purc_class
0.01

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
65_num_ins_3rd
CORRELATION RATIO WITH...
1_cust_subtype
0.03
66_num_ins_firms
MISSING:
---
TOP CATEGORIES
0
5,740
99%
1
81
1%
5
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
66_num_ins_firms
PROVIDES INFORMATION ON...
45_ins_firms
0.79
58_ins_disab
0.18
79_num_ins_disab
0.17
50_ins_lorry
0.17
71_num_ins_lorry
0.16
69_num_ins_van
0.11
48_ins_van
0.10
74_num_ins_agrmac
0.09
53_ins_agr_mach
0.09
72_num_ins_trailer
0.03
51_ins_trailer
0.03
73_num_ins_tractor
0.01
52_ins_tractors
0.01
63_ins_property
0.01

THESE FEATURES
GIVE INFORMATION
ON 66_num_ins_firms:
45_ins_firms
0.99
59_ins_fire
0.13
69_num_ins_van
0.08
48_ins_van
0.08
58_ins_disab
0.07
79_num_ins_disab
0.06
5_cust_type
0.05
27_sc_b2
0.03
53_ins_agr_mach
0.03
80_num_ins_fire
0.03
74_num_ins_agrmac
0.03
30_home_rent
0.03
31_home_ovner
0.03
38_income_45
0.03

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
66_num_ins_firms
CORRELATION RATIO WITH...
1_cust_subtype
0.02
67_num_ins_agr
MISSING:
---
TOP CATEGORIES
0
5,702
98%
1
120
2%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
67_num_ins_agr
PROVIDES INFORMATION ON...
46_ins_agr
0.86
73_num_ins_tractor
0.29
52_ins_tractors
0.27
74_num_ins_agrmac
0.12
53_ins_agr_mach
0.12
72_num_ins_trailer
0.04
51_ins_trailer
0.03
58_ins_disab
0.02
59_ins_fire
0.02
79_num_ins_disab
0.02
56_ins_acc_pri
0.02
80_num_ins_fire
0.01
65_num_ins_3rd
0.01
77_num_ins_acc_pri
0.01

THESE FEATURES
GIVE INFORMATION
ON 67_num_ins_agr:
46_ins_agr
1.00
73_num_ins_tractor
0.39
52_ins_tractors
0.39
59_ins_fire
0.32
5_cust_type
0.11
80_num_ins_fire
0.11
21_ocup_farmer
0.10
44_ins_amnt_3rd
0.09
65_num_ins_3rd
0.08
43_purc_class
0.05
68_num_ins_car
0.04
31_home_ovner
0.04
30_home_rent
0.04
18_educ_low
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
67_num_ins_agr
CORRELATION RATIO WITH...
1_cust_subtype
0.08
68_num_ins_car
MISSING:
---
TOP CATEGORIES
0
2,845
49%
1
2,712
47%
2
246
4%
3
12
<1%
4
5
<1%
7
1
<1%
6
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
68_num_ins_car
PROVIDES INFORMATION ON...
47_ins_car
0.72
71_num_ins_lorry
0.11
50_ins_lorry
0.11
85_num_ins_socsec
0.08
53_ins_agr_mach
0.08
60_ins_surf
0.08
75_num_ins_moped
0.08
64_ins_socsec
0.07
54_ins_moped
0.07
74_num_ins_agrmac
0.07
61_ins_boat
0.06
86_num_ins_caravan
0.05
73_num_ins_tractor
0.04
69_num_ins_van
0.04

THESE FEATURES
GIVE INFORMATION
ON 68_num_ins_car:
47_ins_car
0.83
54_ins_moped
0.02
75_num_ins_moped
0.02
59_ins_fire
0.02
44_ins_amnt_3rd
0.02
65_num_ins_3rd
0.01
86_num_ins_caravan
0.01
5_cust_type
0.01
64_ins_socsec
0.01
85_num_ins_socsec
0.01
73_num_ins_tractor
0.01
52_ins_tractors
0.01
31_home_ovner
0.01
30_home_rent
0.01

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
68_num_ins_car
CORRELATION RATIO WITH...
1_cust_subtype
0.03
69_num_ins_van
MISSING:
---
TOP CATEGORIES
0
5,774
>99%
1
40
<1%
2
4
<1%
3
3
<1%
4
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
69_num_ins_van
PROVIDES INFORMATION ON...
48_ins_van
0.92
50_ins_lorry
0.28
71_num_ins_lorry
0.27
74_num_ins_agrmac
0.16
53_ins_agr_mach
0.13
45_ins_firms
0.10
66_num_ins_firms
0.08
72_num_ins_trailer
0.05
51_ins_trailer
0.05
79_num_ins_disab
0.02
58_ins_disab
0.02
52_ins_tractors
0.01
73_num_ins_tractor
0.01
55_ins_life
0.01

THESE FEATURES
GIVE INFORMATION
ON 69_num_ins_van:
48_ins_van
0.94
45_ins_firms
0.17
59_ins_fire
0.12
66_num_ins_firms
0.11
74_num_ins_agrmac
0.09
53_ins_agr_mach
0.07
50_ins_lorry
0.07
71_num_ins_lorry
0.07
51_ins_trailer
0.07
72_num_ins_trailer
0.06
15_hh_child
0.05
18_educ_low
0.05
5_cust_type
0.05
10_mar_maried
0.05

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
69_num_ins_van
CORRELATION RATIO WITH...
1_cust_subtype
0.03
70_num_ins_moto
MISSING:
---
TOP CATEGORIES
0
5,600
96%
1
211
4%
2
10
<1%
8
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
70_num_ins_moto
PROVIDES INFORMATION ON...
49_ins_moto
0.82
56_ins_acc_pri
0.01
48_ins_van
0.01
51_ins_trailer
0.01
69_num_ins_van
0.01
55_ins_life
0.01
64_ins_socsec
0.01
72_num_ins_trailer
0.01
76_num_ins_life
0.01
77_num_ins_acc_pri
0.01
75_num_ins_moped
0.01
63_ins_property
0.01
74_num_ins_agrmac
0.01
54_ins_moped
0.00

THESE FEATURES
GIVE INFORMATION
ON 70_num_ins_moto:
49_ins_moto
0.97
68_num_ins_car
0.02
5_cust_type
0.02
43_purc_class
0.02
30_home_rent
0.02
10_mar_maried
0.02
59_ins_fire
0.02
31_home_ovner
0.01
29_sc_d
0.01
38_income_45
0.01
14_hh_woclild
0.01
55_ins_life
0.01
47_ins_car
0.01
26_sc_b1
0.01

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
70_num_ins_moto
CORRELATION RATIO WITH...
1_cust_subtype
0.03
71_num_ins_lorry
MISSING:
---
TOP CATEGORIES
0
5,813
>99%
1
6
<1%
2
2
<1%
3
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
71_num_ins_lorry
PROVIDES INFORMATION ON...
50_ins_lorry
0.96
69_num_ins_van
0.07
48_ins_van
0.07
45_ins_firms
0.03
53_ins_agr_mach
0.03
66_num_ins_firms
0.03
74_num_ins_agrmac
0.03
51_ins_trailer
0.02
72_num_ins_trailer
0.02
79_num_ins_disab
0.02
58_ins_disab
0.02
73_num_ins_tractor
0.01
52_ins_tractors
0.01
62_ins_bike
0.00

THESE FEATURES
GIVE INFORMATION
ON 71_num_ins_lorry:
50_ins_lorry
0.94
48_ins_van
0.28
69_num_ins_van
0.27
45_ins_firms
0.24
30_home_rent
0.17
31_home_ovner
0.17
66_num_ins_firms
0.16
25_sc_a
0.15
35_health_pub
0.15
36_health_priv
0.15
18_educ_low
0.14
5_cust_type
0.13
39_income_75
0.13
51_ins_trailer
0.13

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
71_num_ins_lorry
CORRELATION RATIO WITH...
1_cust_subtype
0.02
72_num_ins_trailer
MISSING:
---
TOP CATEGORIES
0
5,757
99%
1
59
1%
2
4
<1%
3
2
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
72_num_ins_trailer
PROVIDES INFORMATION ON...
51_ins_trailer
0.89
60_ins_surf
0.12
81_num_ins_surf
0.11
71_num_ins_lorry
0.10
74_num_ins_agrmac
0.10
50_ins_lorry
0.10
53_ins_agr_mach
0.09
69_num_ins_van
0.06
48_ins_van
0.05
45_ins_firms
0.03
61_ins_boat
0.03
79_num_ins_disab
0.03
66_num_ins_firms
0.03
58_ins_disab
0.03

THESE FEATURES
GIVE INFORMATION
ON 72_num_ins_trailer:
51_ins_trailer
0.99
47_ins_car
0.06
21_ocup_farmer
0.06
5_cust_type
0.06
59_ins_fire
0.06
69_num_ins_van
0.05
45_ins_firms
0.05
74_num_ins_agrmac
0.04
48_ins_van
0.04
15_hh_child
0.04
53_ins_agr_mach
0.04
46_ins_agr
0.04
24_ocup_unskilled
0.04
22_ocup_mid_man
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
72_num_ins_trailer
CORRELATION RATIO WITH...
1_cust_subtype
0.04
73_num_ins_tractor
MISSING:
---
TOP CATEGORIES
0
5,679
98%
1
105
2%
2
29
<1%
4
6
<1%
3
3
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
73_num_ins_tractor
PROVIDES INFORMATION ON...
52_ins_tractors
0.86
67_num_ins_agr
0.39
46_ins_agr
0.34
74_num_ins_agrmac
0.25
53_ins_agr_mach
0.25
71_num_ins_lorry
0.10
50_ins_lorry
0.09
58_ins_disab
0.06
79_num_ins_disab
0.06
56_ins_acc_pri
0.03
51_ins_trailer
0.03
45_ins_firms
0.03
72_num_ins_trailer
0.03
48_ins_van
0.03

THESE FEATURES
GIVE INFORMATION
ON 73_num_ins_tractor:
52_ins_tractors
0.92
46_ins_agr
0.30
67_num_ins_agr
0.29
59_ins_fire
0.26
5_cust_type
0.14
21_ocup_farmer
0.12
80_num_ins_fire
0.06
43_purc_class
0.06
30_home_rent
0.05
31_home_ovner
0.05
53_ins_agr_mach
0.05
74_num_ins_agrmac
0.05
18_educ_low
0.05
68_num_ins_car
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
73_num_ins_tractor
CORRELATION RATIO WITH...
1_cust_subtype
0.10
74_num_ins_agrmac
MISSING:
---
TOP CATEGORIES
0
5,801
>99%
1
12
<1%
2
6
<1%
3
2
<1%
6
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
74_num_ins_agrmac
PROVIDES INFORMATION ON...
53_ins_agr_mach
0.88
69_num_ins_van
0.09
48_ins_van
0.08
71_num_ins_lorry
0.06
50_ins_lorry
0.06
73_num_ins_tractor
0.05
52_ins_tractors
0.05
72_num_ins_trailer
0.04
45_ins_firms
0.04
56_ins_acc_pri
0.04
51_ins_trailer
0.04
79_num_ins_disab
0.03
58_ins_disab
0.03
46_ins_agr
0.03

THESE FEATURES
GIVE INFORMATION
ON 74_num_ins_agrmac:
53_ins_agr_mach
0.91
59_ins_fire
0.29
52_ins_tractors
0.26
73_num_ins_tractor
0.25
5_cust_type
0.20
69_num_ins_van
0.16
21_ocup_farmer
0.16
48_ins_van
0.16
45_ins_firms
0.14
46_ins_agr
0.14
30_home_rent
0.13
31_home_ovner
0.13
67_num_ins_agr
0.12
43_purc_class
0.12

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
74_num_ins_agrmac
CORRELATION RATIO WITH...
1_cust_subtype
0.06
75_num_ins_moped
MISSING:
---
TOP CATEGORIES
0
5,426
93%
1
382
7%
2
14
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
75_num_ins_moped
PROVIDES INFORMATION ON...
54_ins_moped
0.81
80_num_ins_fire
0.03
68_num_ins_car
0.02
65_num_ins_3rd
0.02
47_ins_car
0.02
53_ins_agr_mach
0.02
44_ins_amnt_3rd
0.02
59_ins_fire
0.01
66_num_ins_firms
0.01
84_num_ins_property
0.01
77_num_ins_acc_pri
0.01
69_num_ins_van
0.01
82_num_ins_boat
0.01
48_ins_van
0.01

THESE FEATURES
GIVE INFORMATION
ON 75_num_ins_moped:
54_ins_moped
0.97
59_ins_fire
0.09
80_num_ins_fire
0.08
68_num_ins_car
0.08
47_ins_car
0.08
44_ins_amnt_3rd
0.05
65_num_ins_3rd
0.05
15_hh_child
0.01
5_cust_type
0.01
25_sc_a
0.01
17_educ_med
0.01
21_ocup_farmer
0.01
16_educ_high
0.01
23_ocup_skilled
0.01

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
75_num_ins_moped
CORRELATION RATIO WITH...
1_cust_subtype
0.03
76_num_ins_life
MISSING:
---
TOP CATEGORIES
0
5,529
95%
1
173
3%
2
100
2%
3
11
<1%
4
8
<1%
8
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
76_num_ins_life
PROVIDES INFORMATION ON...
55_ins_life
0.73
78_num_ins_acc_fam
0.10
57_ins_acc_fam
0.09
56_ins_acc_pri
0.03
77_num_ins_acc_pri
0.03
48_ins_van
0.02
69_num_ins_van
0.02
63_ins_property
0.02
65_num_ins_3rd
0.02
45_ins_firms
0.02
44_ins_amnt_3rd
0.01
85_num_ins_socsec
0.01
64_ins_socsec
0.01
61_ins_boat
0.01

THESE FEATURES
GIVE INFORMATION
ON 76_num_ins_life:
55_ins_life
0.84
59_ins_fire
0.06
44_ins_amnt_3rd
0.05
65_num_ins_3rd
0.04
80_num_ins_fire
0.03
5_cust_type
0.03
18_educ_low
0.02
43_purc_class
0.02
47_ins_car
0.02
68_num_ins_car
0.02
39_income_75
0.02
17_educ_med
0.02
25_sc_a
0.02
31_home_ovner
0.02

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
76_num_ins_life
CORRELATION RATIO WITH...
1_cust_subtype
0.07
77_num_ins_acc_pri
MISSING:
---
TOP CATEGORIES
0
5,791
>99%
1
31
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
77_num_ins_acc_pri
PROVIDES INFORMATION ON...
56_ins_acc_pri
0.83
74_num_ins_agrmac
0.04
53_ins_agr_mach
0.03
61_ins_boat
0.01
46_ins_agr
0.01
52_ins_tractors
0.01
73_num_ins_tractor
0.01
82_num_ins_boat
0.00
55_ins_life
0.00
67_num_ins_agr
0.00
76_num_ins_life
0.00
49_ins_moto
0.00
51_ins_trailer
0.00
75_num_ins_moped
0.00

THESE FEATURES
GIVE INFORMATION
ON 77_num_ins_acc_pri:
56_ins_acc_pri
1.00
13_mar_single
0.06
34_car_0
0.04
55_ins_life
0.04
12_mar_other
0.04
27_sc_b2
0.03
59_ins_fire
0.03
74_num_ins_agrmac
0.03
30_home_rent
0.03
5_cust_type
0.03
23_ocup_skilled
0.03
31_home_ovner
0.03
38_income_45
0.03
53_ins_agr_mach
0.03

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
77_num_ins_acc_pri
CORRELATION RATIO WITH...
1_cust_subtype
0.02
78_num_ins_acc_fam
MISSING:
---
TOP CATEGORIES
0
5,784
>99%
1
38
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
78_num_ins_acc_fam
PROVIDES INFORMATION ON...
57_ins_acc_fam
0.90
64_ins_socsec
0.03
85_num_ins_socsec
0.03
76_num_ins_life
0.02
55_ins_life
0.02
83_num_ins_bike
0.01
63_ins_property
0.00
73_num_ins_tractor
0.00
52_ins_tractors
0.00
51_ins_trailer
0.00
65_num_ins_3rd
0.00
84_num_ins_property
0.00
44_ins_amnt_3rd
0.00
59_ins_fire
0.00

THESE FEATURES
GIVE INFORMATION
ON 78_num_ins_acc_fam:
57_ins_acc_fam
1.00
55_ins_life
0.11
76_num_ins_life
0.10
59_ins_fire
0.07
64_ins_socsec
0.07
17_educ_med
0.06
85_num_ins_socsec
0.05
32_car_1
0.05
39_income_75
0.05
14_hh_woclild
0.04
18_educ_low
0.04
44_ins_amnt_3rd
0.04
35_health_pub
0.04
65_num_ins_3rd
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
78_num_ins_acc_fam
CORRELATION RATIO WITH...
1_cust_subtype
0.01
79_num_ins_disab
MISSING:
---
TOP CATEGORIES
0
5,799
>99%
1
19
<1%
2
4
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
79_num_ins_disab
PROVIDES INFORMATION ON...
58_ins_disab
0.92
66_num_ins_firms
0.06
45_ins_firms
0.06
53_ins_agr_mach
0.04
71_num_ins_lorry
0.04
50_ins_lorry
0.04
74_num_ins_agrmac
0.03
51_ins_trailer
0.01
48_ins_van
0.01
69_num_ins_van
0.01
72_num_ins_trailer
0.01
73_num_ins_tractor
0.01
52_ins_tractors
0.01
46_ins_agr
0.01

THESE FEATURES
GIVE INFORMATION
ON 79_num_ins_disab:
58_ins_disab
0.94
45_ins_firms
0.19
66_num_ins_firms
0.17
59_ins_fire
0.15
31_home_ovner
0.10
30_home_rent
0.10
27_sc_b2
0.08
37_income_30
0.07
22_ocup_mid_man
0.06
38_income_45
0.06
35_health_pub
0.06
36_health_priv
0.06
21_ocup_farmer
0.06
73_num_ins_tractor
0.06

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
79_num_ins_disab
CORRELATION RATIO WITH...
1_cust_subtype
0.01
80_num_ins_fire
MISSING:
---
TOP CATEGORIES
1
3,017
52%
0
2,666
46%
2
126
2%
3
7
<1%
4
3
<1%
5
2
<1%
7
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
80_num_ins_fire
PROVIDES INFORMATION ON...
59_ins_fire
0.47
65_num_ins_3rd
0.27
44_ins_amnt_3rd
0.23
67_num_ins_agr
0.11
46_ins_agr
0.10
75_num_ins_moped
0.08
74_num_ins_agrmac
0.08
54_ins_moped
0.07
73_num_ins_tractor
0.06
53_ins_agr_mach
0.06
52_ins_tractors
0.05
56_ins_acc_pri
0.04
45_ins_firms
0.04
79_num_ins_disab
0.04

THESE FEATURES
GIVE INFORMATION
ON 80_num_ins_fire:
59_ins_fire
0.88
44_ins_amnt_3rd
0.23
65_num_ins_3rd
0.23
54_ins_moped
0.03
75_num_ins_moped
0.03
46_ins_agr
0.01
67_num_ins_agr
0.01
55_ins_life
0.01
30_home_rent
0.01
31_home_ovner
0.01
76_num_ins_life
0.01
73_num_ins_tractor
0.01
47_ins_car
0.01
52_ins_tractors
0.01

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
80_num_ins_fire
CORRELATION RATIO WITH...
1_cust_subtype
0.04
81_num_ins_surf
MISSING:
---
TOP CATEGORIES
0
5,819
>99%
1
3
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
81_num_ins_surf
PROVIDES INFORMATION ON...
60_ins_surf
0.93
61_ins_boat
0.02
82_num_ins_boat
0.02
63_ins_property
0.01
84_num_ins_property
0.01
51_ins_trailer
0.01
72_num_ins_trailer
0.01
20_ocup_entp
0.00
86_num_ins_caravan
0.00
35_health_pub
0.00
36_health_priv
0.00
21_ocup_farmer
0.00
25_sc_a
0.00
16_educ_high
0.00

THESE FEATURES
GIVE INFORMATION
ON 81_num_ins_surf:
60_ins_surf
1.00
35_health_pub
0.26
36_health_priv
0.26
61_ins_boat
0.23
38_income_45
0.19
25_sc_a
0.17
27_sc_b2
0.17
16_educ_high
0.16
34_car_0
0.16
20_ocup_entp
0.16
5_cust_type
0.16
63_ins_property
0.15
33_car_2
0.14
19_ocup_high
0.14

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
81_num_ins_surf
CORRELATION RATIO WITH...
1_cust_subtype
0.01
82_num_ins_boat
MISSING:
---
TOP CATEGORIES
0
5,789
>99%
1
31
<1%
2
2
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
82_num_ins_boat
PROVIDES INFORMATION ON...
61_ins_boat
0.80
60_ins_surf
0.14
81_num_ins_surf
0.13
86_num_ins_caravan
0.01
84_num_ins_property
0.01
63_ins_property
0.01
64_ins_socsec
0.01
85_num_ins_socsec
0.01
51_ins_trailer
0.01
56_ins_acc_pri
0.01
72_num_ins_trailer
0.01
77_num_ins_acc_pri
0.01
68_num_ins_car
0.00
75_num_ins_moped
0.00

THESE FEATURES
GIVE INFORMATION
ON 82_num_ins_boat:
61_ins_boat
0.97
86_num_ins_caravan
0.08
42_income_avg
0.05
32_car_1
0.05
38_income_45
0.05
5_cust_type
0.04
7_rel_prot
0.04
47_ins_car
0.04
14_hh_woclild
0.04
68_num_ins_car
0.04
16_educ_high
0.04
30_home_rent
0.04
31_home_ovner
0.04
23_ocup_skilled
0.04

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
82_num_ins_boat
CORRELATION RATIO WITH...
1_cust_subtype
0.03
83_num_ins_bike
MISSING:
---
TOP CATEGORIES
0
5,675
97%
1
111
2%
2
34
<1%
3
2
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
83_num_ins_bike
PROVIDES INFORMATION ON...
62_ins_bike
1.00
71_num_ins_lorry
0.04
57_ins_acc_fam
0.02
78_num_ins_acc_fam
0.02
50_ins_lorry
0.02
76_num_ins_life
0.00
66_num_ins_firms
0.00
63_ins_property
0.00
64_ins_socsec
0.00
77_num_ins_acc_pri
0.00
82_num_ins_boat
0.00
45_ins_firms
0.00
79_num_ins_disab
0.00
58_ins_disab
0.00

THESE FEATURES
GIVE INFORMATION
ON 83_num_ins_bike:
62_ins_bike
0.88
24_ocup_unskilled
0.03
18_educ_low
0.02
19_ocup_high
0.02
59_ins_fire
0.02
32_car_1
0.02
42_income_avg
0.02
21_ocup_farmer
0.02
35_health_pub
0.02
34_car_0
0.02
5_cust_type
0.02
16_educ_high
0.02
10_mar_maried
0.02
36_health_priv
0.02

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
83_num_ins_bike
CORRELATION RATIO WITH...
1_cust_subtype
0.02
84_num_ins_property
MISSING:
---
TOP CATEGORIES
0
5,777
>99%
1
44
<1%
2
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
84_num_ins_property
PROVIDES INFORMATION ON...
63_ins_property
0.82
60_ins_surf
0.13
81_num_ins_surf
0.12
61_ins_boat
0.02
82_num_ins_boat
0.01
51_ins_trailer
0.01
72_num_ins_trailer
0.01
64_ins_socsec
0.00
45_ins_firms
0.00
57_ins_acc_fam
0.00
78_num_ins_acc_fam
0.00
66_num_ins_firms
0.00
85_num_ins_socsec
0.00
76_num_ins_life
0.00

THESE FEATURES
GIVE INFORMATION
ON 84_num_ins_property:
63_ins_property
0.99
12_mar_other
0.04
25_sc_a
0.04
18_educ_low
0.04
10_mar_maried
0.04
59_ins_fire
0.04
32_car_1
0.03
36_health_priv
0.03
44_ins_amnt_3rd
0.03
26_sc_b1
0.03
35_health_pub
0.03
34_car_0
0.03
28_sc_c
0.03
4_avg_age
0.03

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
84_num_ins_property
CORRELATION RATIO WITH...
1_cust_subtype
0.02
85_num_ins_socsec
MISSING:
---
TOP CATEGORIES
0
5,740
99%
1
81
1%
2
1
<1%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
85_num_ins_socsec
PROVIDES INFORMATION ON...
64_ins_socsec
0.84
78_num_ins_acc_fam
0.05
57_ins_acc_fam
0.05
82_num_ins_boat
0.02
63_ins_property
0.01
68_num_ins_car
0.01
86_num_ins_caravan
0.01
48_ins_van
0.00
47_ins_car
0.00
61_ins_boat
0.00
76_num_ins_life
0.00
69_num_ins_van
0.00
84_num_ins_property
0.00
55_ins_life
0.00

THESE FEATURES
GIVE INFORMATION
ON 85_num_ins_socsec:
64_ins_socsec
0.99
68_num_ins_car
0.08
47_ins_car
0.06
10_mar_maried
0.04
5_cust_type
0.04
23_ocup_skilled
0.04
59_ins_fire
0.04
43_purc_class
0.04
37_income_30
0.03
13_mar_single
0.03
14_hh_woclild
0.03
57_ins_acc_fam
0.03
34_car_0
0.03
78_num_ins_acc_fam
0.03

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
85_num_ins_socsec
CORRELATION RATIO WITH...
1_cust_subtype
0.06
86_num_ins_caravan
MISSING:
---
TOP CATEGORIES
0
5,474
94%
1
348
6%
ALL
5,822
100%
CATEGORICAL ASSOCIATIONS
(UNCERTAINTY COEFFICIENT, 0 to 1)
86_num_ins_caravan
PROVIDES INFORMATION ON...
82_num_ins_boat
0.08
61_ins_boat
0.07
60_ins_surf
0.06
81_num_ins_surf
0.04
85_num_ins_socsec
0.02
64_ins_socsec
0.02
47_ins_car
0.02
79_num_ins_disab
0.02
58_ins_disab
0.02
57_ins_acc_fam
0.02
68_num_ins_car
0.01
78_num_ins_acc_fam
0.01
74_num_ins_agrmac
0.01
59_ins_fire
0.01

THESE FEATURES
GIVE INFORMATION
ON 86_num_ins_caravan:
47_ins_car
0.07
59_ins_fire
0.05
68_num_ins_car
0.05
5_cust_type
0.03
42_income_avg
0.03
43_purc_class
0.03
37_income_30
0.02
18_educ_low
0.02
44_ins_amnt_3rd
0.02
34_car_0
0.02
65_num_ins_3rd
0.02
30_home_rent
0.02
31_home_ovner
0.02
25_sc_a
0.02

NUMERICAL ASSOCIATIONS
(CORRELATION RATIO, 0 to 1)
86_num_ins_caravan
CORRELATION RATIO WITH...
1_cust_subtype
0.07
In [26]:
compare_report = sv.compare([data_train, "train"],[data_test, "test"])
compare_report.show_html("compare.html")

                                             |                                                                …
Report compare.html was generated! NOTEBOOK/COLAB USERS: the web browser MAY not pop up, regardless, the report IS saved in your notebook/colab files.
In [ ]:
IPython.display.HTML('compare.html')# si no funciona display por favor mirar a HTMLs auxiliares.

Los resultados de comparación (compare.html), nos muestran que nuestros datos de training y test son similares. Data_test se puede usar posteriormente para las validaciones y predicciones del modelo.

La variable objetivo de este proyecto es '86_num_ins_caravan', ya que nuestra misión es crear un modelo que prediga quién estará interesadoen comprar un seguro de autocaravanas. Por tanto, vamos a proceder a analizarla. En nuestro caso, esta variable es '86_num_ins_caravan'

In [29]:
data_train ['86_num_ins_caravan'].value_counts()
Out[29]:
0    5474
1     348
Name: 86_num_ins_caravan, dtype: int64

Procedemos a crear un data frame con un conteo de los datos de la variable objetivo.

In [30]:
df_caravan = data_train ['86_num_ins_caravan'].value_counts(normalize=True).mul(100).rename('percent').reset_index()
df_caravan_conteo = data_train['86_num_ins_caravan'].value_counts().reset_index()
df_caravan_pc = pd.merge(df_caravan, df_caravan_conteo, on=['index'], how='inner')
df_caravan_pc
df_caravan
Out[30]:
index percent
0 0 94.022673
1 1 5.977327

Observamos que 5474 personas no poseen una poliza de seguro para caravana, lo que equivale a un poco más del 94% de la muestra, mientras que solo 348 poseen una póliza de caravana, el equivalente a casi el 6% de la muestra.

Análisis de la Correlación¶

In [31]:
# warnings.filterwarnings('ignore')
def plot_feature(df, col_name, isContinuous, target):
   
    f, (ax1, ax2) = plt.subplots(nrows=1, ncols=2, figsize=(12,3), dpi=90)

    count_null = df[col_name].isnull().sum()
    if isContinuous:

        sns.histplot(df.loc[df[col_name].notnull(), col_name], kde=False, ax=ax1)
    else:
        sns.countplot(df[col_name], order=sorted(df[col_name].unique()), color='#5975A4', saturation=1, ax=ax1)
    ax1.set_xlabel(col_name)
    ax1.set_ylabel('Count')
    ax1.set_title(col_name+ ' Numero de nulos: '+str(count_null))
    plt.xticks(rotation = 90)


    if isContinuous:
        sns.boxplot(x=col_name, y=target, data=df, ax=ax2)
        ax2.set_ylabel('')
        ax2.set_title(col_name + ' by '+target)
    else:
        data = df.groupby(col_name)[target].value_counts(normalize=True).to_frame('proportion').reset_index()
        data.columns = [i, target, 'proportion']
        #sns.barplot(x = col_name, y = 'proportion', hue= target, data = data, saturation=1, ax=ax2)
        sns.barplot(x = col_name, y = 'proportion', hue= target, data = data, saturation=1, ax=ax2)
        ax2.set_ylabel(target+' fraction')
        ax2.set_title(target)
        plt.xticks(rotation = 90)
    ax2.set_xlabel(col_name)

    plt.tight_layout()
for i in list(data_train.columns):
    if (data_train[i].dtype==float) & (i!='Number_of_mobile_home_policies'):
        plt_feature(data_train, col_name=i, isContinuous=True, target='86_num_ins_caravan')
    elif  i!='86_num_ins_caravan':
        plot_feature(data_train, col_name=i, isContinuous=False, target='86_num_ins_caravan')

Con data_trian.describe() obtenemos los principales estadísticos de las variables de nuestro modelo.

In [32]:
data_train.describe()
Out[32]:
1_cust_subtype 2_num_houses 3_avg_hh_size 4_avg_age 5_cust_type 6_rel_cat 7_rel_prot 8_rel_other 9_rel_none 10_mar_maried ... 77_num_ins_acc_pri 78_num_ins_acc_fam 79_num_ins_disab 80_num_ins_fire 81_num_ins_surf 82_num_ins_boat 83_num_ins_bike 84_num_ins_property 85_num_ins_socsec 86_num_ins_caravan
count 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 ... 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000 5822.000000
mean 24.253349 1.110615 2.678805 2.991240 5.773617 0.696496 4.626932 1.069907 3.258502 6.183442 ... 0.005325 0.006527 0.004638 0.570079 0.000515 0.006012 0.031776 0.007901 0.014256 0.059773
std 12.846706 0.405842 0.789835 0.814589 2.856760 1.003234 1.715843 1.017503 1.597647 1.909482 ... 0.072782 0.080532 0.077403 0.562058 0.022696 0.081632 0.210986 0.090463 0.119996 0.237087
min 1.000000 1.000000 1.000000 1.000000 1.000000 0.000000 0.000000 0.000000 0.000000 0.000000 ... 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
25% 10.000000 1.000000 2.000000 2.000000 3.000000 0.000000 4.000000 0.000000 2.000000 5.000000 ... 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
50% 30.000000 1.000000 3.000000 3.000000 7.000000 0.000000 5.000000 1.000000 3.000000 6.000000 ... 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
75% 35.000000 1.000000 3.000000 3.000000 8.000000 1.000000 6.000000 2.000000 4.000000 7.000000 ... 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
max 41.000000 10.000000 5.000000 6.000000 10.000000 9.000000 9.000000 5.000000 9.000000 9.000000 ... 1.000000 1.000000 2.000000 7.000000 1.000000 2.000000 3.000000 2.000000 2.000000 1.000000

8 rows × 86 columns

In [33]:
corr = data_train.corr(method = 'spearman')
In [34]:
plt.figure(figsize = (10, 8))
sns.heatmap(corr.abs(), cmap ='viridis' )
plt.show()

La correlación nos muestra que la mayoría de las variables sociodemográficas (1-43) tienen muy poco efecto sobre la compra de productos. Dudamos que pueda tener la misma realción sobre nuestra variable objetivo.

A parte de la diagonal amarilla, observamos que hay otras dos. Nos enseñan que variables tipo 'contrubition..' y 'number of..' coinciden en niveles muy altos.

In [35]:
new_corr = corr.abs()
new_corr.loc[:,:] = np.tril(new_corr, k=-1) 
new_corr = new_corr.stack().to_frame('correlation').reset_index().sort_values(by='correlation', ascending=False)
In [36]:
new_corr[new_corr.correlation > 0.6]
Out[36]:
level_0 level_1 correlation
6939 81_num_ins_surf 60_ins_surf 1.000000
6069 71_num_ins_lorry 50_ins_lorry 1.000000
6330 74_num_ins_agrmac 53_ins_agr_mach 0.999999
6765 79_num_ins_disab 58_ins_disab 0.999998
6591 77_num_ins_acc_pri 56_ins_acc_pri 0.999996
6678 78_num_ins_acc_fam 57_ins_acc_fam 0.999995
7026 82_num_ins_boat 61_ins_boat 0.999995
5895 69_num_ins_van 48_ins_van 0.999994
7200 84_num_ins_property 63_ins_property 0.999992
6156 72_num_ins_trailer 51_ins_trailer 0.999989
7287 85_num_ins_socsec 64_ins_socsec 0.999970
5634 66_num_ins_firms 45_ins_firms 0.999970
6243 73_num_ins_tractor 52_ins_tractors 0.999956
5721 67_num_ins_agr 46_ins_agr 0.999944
7113 83_num_ins_bike 62_ins_bike 0.999939
5982 70_num_ins_moto 49_ins_moto 0.999814
2609 31_home_ovner 30_home_rent 0.999549
6417 75_num_ins_moped 54_ins_moped 0.999482
6504 76_num_ins_life 55_ins_life 0.999237
3044 36_health_priv 35_health_pub 0.999203
5547 65_num_ins_3rd 44_ins_amnt_3rd 0.989286
344 5_cust_type 1_cust_subtype 0.987949
5808 68_num_ins_car 47_ins_car 0.949831
6852 80_num_ins_fire 59_ins_fire 0.915881
955 12_mar_other 10_mar_maried 0.883178
1206 15_hh_child 3_avg_hh_size 0.807787
1478 18_educ_low 17_educ_med 0.750358
694 9_rel_none 7_rel_prot 0.745142
1043 13_mar_single 12_mar_other 0.736695
2082 25_sc_a 19_ocup_high 0.698684
3562 42_income_avg 37_income_30 0.695377
2869 34_car_0 32_car_1 0.691084
2079 25_sc_a 16_educ_high 0.679367
1041 13_mar_single 10_mar_maried 0.672435
2339 28_sc_c 18_educ_low 0.644443
2849 34_car_0 12_mar_other 0.644399
1477 18_educ_low 16_educ_high 0.636033
3564 42_income_avg 39_income_75 0.630481
1034 13_mar_single 3_avg_hh_size 0.626314
2847 34_car_0 10_mar_maried 0.615513
2344 28_sc_c 23_ocup_skilled 0.604976
1216 15_hh_child 13_mar_single 0.602847

Como vemos, las variables 'number...' y 'Contribution...' tienen una correlación casi de 1. Por ello, para la prediccion, seria recomendable quitar uno de ellos. Las variables 'Number...' tienen un poco mas variación, por eso quitamos las variables de "Contribution..."

In [ ]:
#Con el siguiente código, podemos quitar variables 'contribution...'. tanto en entrenamiento y test.

#data_train.drop(['44_ins_amnt_3rd','45_ins_firms',
#                '46_ins_agr','47_ins_car','48_ins_van','49_ins_moto','50_ins_lorry',
#                '51_ins_trailer','52_ins_tractors','53_ins_agr_mach','54_ins_moped','55_ins_life',
#                '56_ins_acc_pri','57_ins_acc_fam','58_ins_disab','59_ins_fire','60_ins_surf',
#               '61_ins_boat','62_ins_bike','63_ins_property','64_ins_socsec'], axis=1, inplace= True)
In [17]:
data_train
Out[17]:
1_cust_subtype 2_num_houses 3_avg_hh_size 4_avg_age 5_cust_type 6_rel_cat 7_rel_prot 8_rel_other 9_rel_none 10_mar_maried ... 77_num_ins_acc_pri 78_num_ins_acc_fam 79_num_ins_disab 80_num_ins_fire 81_num_ins_surf 82_num_ins_boat 83_num_ins_bike 84_num_ins_property 85_num_ins_socsec 86_num_ins_caravan
0 33 1 3 2 8 0 5 1 3 7 ... 0 0 0 1 0 0 0 0 0 0
1 37 1 2 2 8 1 4 1 4 6 ... 0 0 0 1 0 0 0 0 0 0
2 37 1 2 2 8 0 4 2 4 3 ... 0 0 0 1 0 0 0 0 0 0
3 9 1 3 3 3 2 3 2 4 5 ... 0 0 0 1 0 0 0 0 0 0
4 40 1 4 2 10 1 4 1 4 7 ... 0 0 0 1 0 0 0 0 0 0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
5817 36 1 1 2 8 0 6 1 2 1 ... 0 0 0 1 0 0 0 0 0 0
5818 35 1 4 4 8 1 4 1 4 6 ... 0 0 0 1 0 0 0 0 0 0
5819 33 1 3 4 8 0 6 0 3 5 ... 0 0 0 1 0 0 0 0 0 1
5820 34 1 3 2 8 0 7 0 2 7 ... 0 0 0 0 0 0 0 0 0 0
5821 33 1 3 3 8 0 6 1 2 7 ... 0 0 0 0 0 0 0 0 0 0

5822 rows × 65 columns

Ahora, analizamos las distribuciones con los gráficos.

In [38]:
def plot_histograms(df, columns):
    # keep total number of subplot
    k = len(data_train.columns)
    # n = number of chart columns
    n = columns
    m = (k - 1) // n + 1
    
    # Create figure
    fig, axes = plt.subplots(m, n, figsize=(n * 5, m * 3))

    # Iterate through columns, tracking the column name and 
    # which number we are at i. Within each iteration, plot
    for i, (name, col) in enumerate(data_train.iteritems()):
        r, c = i // n, i % n
        ax = axes[r, c]
        # the histogram
        col.hist(ax=ax)
        # kde = Kernel Density Estimate plot
        ax2 = col.plot.kde(ax=ax, secondary_y=True, title=name)
        ax2.set_ylim(0)

    # Use tight_layout() as an easy way to sharpen up the layout spacing
    fig.tight_layout()
In [39]:
plot_histograms(df=data_train[['86_num_ins_caravan', '1_cust_subtype', '78_num_ins_acc_fam']], columns=4)

Las variables explicativas no tienen una distribución normal. Queremos que los clientes compren un seguro de autocaravanas, pero el porcentaje de ellos es muy pequeño. Por eso, aunque aperezcan algunas variables como outliers, en este tipo de distribuciones puede tener un significado, ya que nuestra misión es vender más seguros de autocaravana. En el modelo de predicción, mantenemos los valores con poca densidad. En un modelo con probabilidades o logístico puede tener sentido.

Ahora, hemos filtrado nuestra correlación entre los valores 0.4 y 0.6.

In [40]:
new_corr[(new_corr.correlation > 0.4)& (new_corr.correlation <0.6)]
Out[40]:
level_0 level_1 correlation
2081 25_sc_a 18_educ_low 0.585141
3028 36_health_priv 19_ocup_high 0.583322
2942 35_health_pub 19_ocup_high 0.581878
1217 15_hh_child 14_hh_woclild 0.567282
6858 80_num_ins_fire 65_num_ins_3rd 0.563030
... ... ... ...
1290 16_educ_high 1_cust_subtype 0.414986
1822 22_ocup_mid_man 17_educ_med 0.412728
3550 42_income_avg 25_sc_a 0.412440
3292 39_income_75 25_sc_a 0.411522
1995 24_ocup_unskilled 18_educ_low 0.404311

64 rows × 3 columns

In [41]:
new_corr[new_corr.level_1 == '1_cust_subtype']
Out[41]:
level_0 level_1 correlation
344 5_cust_type 1_cust_subtype 0.987949
1462 18_educ_low 1_cust_subtype 0.473573
1290 16_educ_high 1_cust_subtype 0.414986
3612 43_purc_class 1_cust_subtype 0.368700
2322 28_sc_c 1_cust_subtype 0.343425
... ... ... ...
5246 62_ins_bike 1_cust_subtype 0.003642
1032 13_mar_single 1_cust_subtype 0.003192
4128 49_ins_moto 1_cust_subtype 0.001139
5934 70_num_ins_moto 1_cust_subtype 0.000998
0 1_cust_subtype 1_cust_subtype 0.000000

86 rows × 3 columns

La variable 1 incluye factores sociodemográficos y luego hay otras 42 que analizan la relación que existe entre uno y otro. varibale 5 customer type tiene más por que customer type y customer subtype deberian ir más o menos paralelas, pero la variable 1 tiene mas categorias. En esta comparación, comparamos variable 1 contra 5.

Es imprescindible que las otras variables sociodemográficas esten relacionados. Los valores importantes se pueden mantener sabiendo el coste o poner en un modelo de probabilidad condicional.

Las variables de compra (44-85) no parecen correladas con la variable 1.

In [19]:
#data_train.drop(['5_cust_type'], axis=1, inplace= True)

Finalmente, no hemos hecho ningun encoding. Añadir mas dummies no nos proporciona más información y al añadir más variables va a dismunir, por ejemplo, "degrees of freedoms in tests" lo que ocasionaría overfit. Por eso preferirimos quitar variables en model de predicción, como el "5_cust_type".

Los datos cambiados se puede guardar en proxima path con codigo abajo.

In [20]:
#data_train.to_csv('..//data/processed/data_processed.csv')